The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational per...The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational performance. Despite numerous data-driven methods reported in existing research for battery SOH estimation, these methods often exhibit inconsistent performance across different application scenarios. To address this issue and overcome the performance limitations of individual data-driven models,integrating multiple models for SOH estimation has received considerable attention. Ensemble learning(EL) typically leverages the strengths of multiple base models to achieve more robust and accurate outputs. However, the lack of a clear review of current research hinders the further development of ensemble methods in SOH estimation. Therefore, this paper comprehensively reviews multi-model ensemble learning methods for battery SOH estimation. First, existing ensemble methods are systematically categorized into 6 classes based on their combination strategies. Different realizations and underlying connections are meticulously analyzed for each category of EL methods, highlighting distinctions, innovations, and typical applications. Subsequently, these ensemble methods are comprehensively compared in terms of base models, combination strategies, and publication trends. Evaluations across 6 dimensions underscore the outstanding performance of stacking-based ensemble methods. Following this, these ensemble methods are further inspected from the perspectives of weighted ensemble and diversity, aiming to inspire potential approaches for enhancing ensemble performance. Moreover, addressing challenges such as base model selection, measuring model robustness and uncertainty, and interpretability of ensemble models in practical applications is emphasized. Finally, future research prospects are outlined, specifically noting that deep learning ensemble is poised to advance ensemble methods for battery SOH estimation. The convergence of advanced machine learning with ensemble learning is anticipated to yield valuable avenues for research. Accelerated research in ensemble learning holds promising prospects for achieving more accurate and reliable battery SOH estimation under real-world conditions.展开更多
In this study,we conducted an experiment to construct multi-model ensemble(MME)predictions for the El Niño-Southern Oscillation(ENSO)using a neural network,based on hindcast data released from five coupled oceana...In this study,we conducted an experiment to construct multi-model ensemble(MME)predictions for the El Niño-Southern Oscillation(ENSO)using a neural network,based on hindcast data released from five coupled oceanatmosphere models,which exhibit varying levels of complexity.This nonlinear approach demonstrated extraordinary superiority and effectiveness in constructing ENSO MME.Subsequently,we employed the leave-one-out crossvalidation and the moving base methods to further validate the robustness of the neural network model in the formulation of ENSO MME.In conclusion,the neural network algorithm outperforms the conventional approach of assigning a uniform weight to all models.This is evidenced by an enhancement in correlation coefficients and reduction in prediction errors,which have the potential to provide a more accurate ENSO forecast.展开更多
With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration predict...With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration prediction system is of great scientific and practical significance for accurate and reliable predictions.This paper proposes a combination of pointinterval prediction system for pollutant concentration prediction by leveraging neural network,meta-heuristic optimization algorithm,and fuzzy theory.Fuzzy information granulation technology is used in data preprocessing to transform numerical sequences into fuzzy particles for comprehensive feature extraction.The golden Jackal optimization algorithm is employed in the optimization stage to fine-tune model hyperparameters.In the prediction stage,an ensemble learning method combines training results frommultiplemodels to obtain final point predictions while also utilizing quantile regression and kernel density estimation methods for interval predictions on the test set.Experimental results demonstrate that the combined model achieves a high goodness of fit coefficient of determination(R^(2))at 99.3% and a maximum difference between prediction accuracy mean absolute percentage error(MAPE)and benchmark model at 12.6%.This suggests that the integrated learning system proposed in this paper can provide more accurate deterministic predictions as well as reliable uncertainty analysis compared to traditionalmodels,offering practical reference for air quality early warning.展开更多
This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble lear...This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble learning techniques:DAGGING(DG),MULTIBOOST(MB),and ADABOOST(AB).This combination resulted in three distinct ensemble models:DG-RBFN,MB-RBFN,and AB-RBFN.Additionally,a traditional weighted method,Information Value(IV),and a benchmark machine learning(ML)model,Multilayer Perceptron Neural Network(MLP),were employed for comparison and validation.The models were developed using ten landslide conditioning factors,which included slope,aspect,elevation,curvature,land cover,geomorphology,overburden depth,lithology,distance to rivers and distance to roads.These factors were instrumental in predicting the output variable,which was the probability of landslide occurrence.Statistical analysis of the models’performance indicated that the DG-RBFN model,with an Area Under ROC Curve(AUC)of 0.931,outperformed the other models.The AB-RBFN model achieved an AUC of 0.929,the MB-RBFN model had an AUC of 0.913,and the MLP model recorded an AUC of 0.926.These results suggest that the advanced ensemble ML model DG-RBFN was more accurate than traditional statistical model,single MLP model,and other ensemble models in preparing trustworthy landslide susceptibility maps,thereby enhancing land use planning and decision-making.展开更多
Objective To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data.Methods Clinical indicators,echocar...Objective To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data.Methods Clinical indicators,echocardiographic data,traditional Chinese medicine(TCM)tongue manifestations,and facial features were collected from patients who underwent coro-nary computed tomography angiography(CTA)in the Cardiac Care Unit(CCU)of Shanghai Tenth People's Hospital between May 1,2023 and May 1,2024.An adaptive weighted multi-modal data fusion(AWMDF)model based on deep learning was constructed to predict the severity of coronary artery stenosis.The model was evaluated using metrics including accura-cy,precision,recall,F1 score,and the area under the receiver operating characteristic(ROC)curve(AUC).Further performance assessment was conducted through comparisons with six ensemble machine learning methods,data ablation,model component ablation,and various decision-level fusion strategies.Results A total of 158 patients were included in the study.The AWMDF model achieved ex-cellent predictive performance(AUC=0.973,accuracy=0.937,precision=0.937,recall=0.929,and F1 score=0.933).Compared with model ablation,data ablation experiments,and various traditional machine learning models,the AWMDF model demonstrated superior per-formance.Moreover,the adaptive weighting strategy outperformed alternative approaches,including simple weighting,averaging,voting,and fixed-weight schemes.Conclusion The AWMDF model demonstrates potential clinical value in the non-invasive prediction of coronary artery disease and could serve as a tool for clinical decision support.展开更多
Smart manufacturing and Industry 4.0 are transforming traditional manufacturing processes by utilizing innovative technologies such as the artificial intelligence(AI)and internet of things(IoT)to enhance efficiency,re...Smart manufacturing and Industry 4.0 are transforming traditional manufacturing processes by utilizing innovative technologies such as the artificial intelligence(AI)and internet of things(IoT)to enhance efficiency,reduce costs,and ensure product quality.In light of the recent advancement of Industry 4.0,identifying defects has become important for ensuring the quality of products during the manufacturing process.In this research,we present an ensemble methodology for accurately classifying hot rolled steel surface defects by combining the strengths of four pre-trained convolutional neural network(CNN)architectures:VGG16,VGG19,Xception,and Mobile-Net V2,compensating for their individual weaknesses.We evaluated our methodology on the Xsteel surface defect dataset(XSDD),which comprises seven different classes.The ensemble methodology integrated the predictions of individual models through two methods:model averaging and weighted averaging.Our evaluation showed that the model averaging ensemble achieved an accuracy of 98.89%,a recall of 98.92%,a precision of 99.05%,and an F1-score of 98.97%,while the weighted averaging ensemble reached an accuracy of 99.72%,a recall of 99.74%,a precision of 99.67%,and an F1-score of 99.70%.The proposed weighted averaging ensemble model outperformed the model averaging method and the individual models in detecting defects in terms of accuracy,recall,precision,and F1-score.Comparative analysis with recent studies also showed the superior performance of our methodology.展开更多
As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigat...As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigation of degradation mechanisms.However,dynamic operating conditions,cell-to-cell inconsistencies,and limited availability of labeled data have posed significant challenges to accurate and robust prognosis and diagnosis.Herein,we introduce a time-series-decomposition-based ensembled lightweight learning model(TELL-Me),which employs a synergistic dual-module framework to facilitate accurate and reliable forecasting.The feature module formulates features with physical implications and sheds light on battery aging mechanisms,while the gradient module monitors capacity degradation rates and captures aging trend.TELL-Me achieves high accuracy in end-of-life prediction using minimal historical data from a single battery without requiring offline training dataset,and demonstrates impressive generality and robustness across various operating conditions and battery types.Additionally,by correlating feature contributions with degradation mechanisms across different datasets,TELL-Me is endowed with the diagnostic ability that not only enhances prediction reliability but also provides critical insights into the design and optimization of next-generation batteries.展开更多
Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning(ML) models have proven to be effective tools for assessin...Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning(ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following:(1) The stacking ensemble learning, using RF-XGBCB-LR model, significantly enhances flood susceptibility simulation.(2) In addition to rainfall,key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland.(3) In the northeast of the study area,heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management.展开更多
Small-drone technology has opened a range of new applications for aerial transportation. These drones leverage the Internet of Things (IoT) to offer cross-location services for navigation. However, they are susceptibl...Small-drone technology has opened a range of new applications for aerial transportation. These drones leverage the Internet of Things (IoT) to offer cross-location services for navigation. However, they are susceptible to security and privacy threats due to hardware and architectural issues. Although small drones hold promise for expansion in both civil and defense sectors, they have safety, security, and privacy threats. Addressing these challenges is crucial to maintaining the security and uninterrupted operations of these drones. In this regard, this study investigates security, and preservation concerning both the drones and Internet of Drones (IoD), emphasizing the significance of creating drone networks that are secure and can robustly withstand interceptions and intrusions. The proposed framework incorporates a weighted voting ensemble model comprising three convolutional neural network (CNN) models to enhance intrusion detection within the network. The employed CNNs are customized 1D models optimized to obtain better performance. The output from these CNNs is voted using a weighted criterion using a 0.4, 0.3, and 0.3 ratio for three CNNs, respectively. Experiments involve using multiple benchmark datasets, achieving an impressive accuracy of up to 99.89% on drone data. The proposed model shows promising results concerning precision, recall, and F1 as indicated by their obtained values of 99.92%, 99.98%, and 99.97%, respectively. Furthermore, cross-validation and performance comparison with existing works is also carried out. Findings indicate that the proposed approach offers a prospective solution for detecting security threats for aerial systems and satellite systems with high accuracy.展开更多
In this paper,we consider the Fisher informations among three classical type β-ensembles when β>0 scales with n satisfying lim βn=∞.We offer the exact order of-the corresponding two Fisher informations,which in...In this paper,we consider the Fisher informations among three classical type β-ensembles when β>0 scales with n satisfying lim βn=∞.We offer the exact order of-the corresponding two Fisher informations,which indicates that theβ-Laguerre ensembles do not satisfy the logarithmic Sobolev inequality.We also give some limit theorems on the extremals of β-Jacobi ensembles for β>0 fixed.展开更多
Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or ...Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or obtaining entity related external knowledge from knowledge bases or Large Language Models(LLMs).However,these approaches ignore the poor semantic correlation between visual and textual modalities in MNER datasets and do not explore different multi-modal fusion approaches.In this paper,we present MMAVK,a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion,which aims to leverage the Multi-modal Large Language Model(MLLM)as an implicit knowledge base.It also extracts vision-based auxiliary knowledge from the image formore accurate and effective recognition.Specifically,we propose vision-based auxiliary knowledge generation,which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts,thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs.Furthermore,we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformerbased encoder.Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNER datasets,even when the largemodels employed have significantly fewer parameters than other baselines.展开更多
Multi-modal knowledge graph completion(MMKGC)aims to complete missing entities or relations in multi-modal knowledge graphs,thereby discovering more previously unknown triples.Due to the continuous growth of data and ...Multi-modal knowledge graph completion(MMKGC)aims to complete missing entities or relations in multi-modal knowledge graphs,thereby discovering more previously unknown triples.Due to the continuous growth of data and knowledge and the limitations of data sources,the visual knowledge within the knowledge graphs is generally of low quality,and some entities suffer from the issue of missing visual modality.Nevertheless,previous studies of MMKGC have primarily focused on how to facilitate modality interaction and fusion while neglecting the problems of low modality quality and modality missing.In this case,mainstream MMKGC models only use pre-trained visual encoders to extract features and transfer the semantic information to the joint embeddings through modal fusion,which inevitably suffers from problems such as error propagation and increased uncertainty.To address these problems,we propose a Multi-modal knowledge graph Completion model based on Super-resolution and Detailed Description Generation(MMCSD).Specifically,we leverage a pre-trained residual network to enhance the resolution and improve the quality of the visual modality.Moreover,we design multi-level visual semantic extraction and entity description generation,thereby further extracting entity semantics from structural triples and visual images.Meanwhile,we train a variational multi-modal auto-encoder and utilize a pre-trained multi-modal language model to complement the missing visual features.We conducted experiments on FB15K-237 and DB13K,and the results showed that MMCSD can effectively perform MMKGC and achieve state-of-the-art performance.展开更多
Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status...Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status.Each of these methods contributes unique diagnostic insights,enhancing the overall assessment of patient condition.Nevertheless,the amalgamation of data from multiple modalities presents difficulties due to disparities in resolution,data collection methods,and noise levels.While traditional models like Convolutional Neural Networks(CNNs)excel in single-modality tasks,they struggle to handle multi-modal complexities,lacking the capacity to model global relationships.This research presents a novel approach for examining multi-modal medical imagery using a transformer-based system.The framework employs self-attention and cross-attention mechanisms to synchronize and integrate features across various modalities.Additionally,it shows resilience to variations in noise and image quality,making it adaptable for real-time clinical use.To address the computational hurdles linked to transformer models,particularly in real-time clinical applications in resource-constrained environments,several optimization techniques have been integrated to boost scalability and efficiency.Initially,a streamlined transformer architecture was adopted to minimize the computational load while maintaining model effectiveness.Methods such as model pruning,quantization,and knowledge distillation have been applied to reduce the parameter count and enhance the inference speed.Furthermore,efficient attention mechanisms such as linear or sparse attention were employed to alleviate the substantial memory and processing requirements of traditional self-attention operations.For further deployment optimization,researchers have implemented hardware-aware acceleration strategies,including the use of TensorRT and ONNX-based model compression,to ensure efficient execution on edge devices.These optimizations allow the approach to function effectively in real-time clinical settings,ensuring viability even in environments with limited resources.Future research directions include integrating non-imaging data to facilitate personalized treatment and enhancing computational efficiency for implementation in resource-limited environments.This study highlights the transformative potential of transformer models in multi-modal medical imaging,offering improvements in diagnostic accuracy and patient care outcomes.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
To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities...To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.展开更多
Traditional Chinese medicine(TCM)demonstrates distinctive advantages in disease prevention and treatment.However,analyzing its biological mechanisms through the modern medical research paradigm of“single drug,single ...Traditional Chinese medicine(TCM)demonstrates distinctive advantages in disease prevention and treatment.However,analyzing its biological mechanisms through the modern medical research paradigm of“single drug,single target”presents significant challenges due to its holistic approach.Network pharmacology and its core theory of network targets connect drugs and diseases from a holistic and systematic perspective based on biological networks,overcoming the limitations of reductionist research models and showing considerable value in TCM research.Recent integration of network target computational and experimental methods with artificial intelligence(AI)and multi-modal multi-omics technologies has substantially enhanced network pharmacology methodology.The advancement in computational and experimental techniques provides complementary support for network target theory in decoding TCM principles.This review,centered on network targets,examines the progress of network target methods combined with AI in predicting disease molecular mechanisms and drug-target relationships,alongside the application of multi-modal multi-omics technologies in analyzing TCM formulae,syndromes,and toxicity.Looking forward,network target theory is expected to incorporate emerging technologies while developing novel approaches aligned with its unique characteristics,potentially leading to significant breakthroughs in TCM research and advancing scientific understanding and innovation in TCM.展开更多
As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advan...As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.展开更多
The primary objective of Chinese spelling correction(CSC)is to detect and correct erroneous characters in Chinese text,which can result from various factors,such as inaccuracies in pinyin representation,character rese...The primary objective of Chinese spelling correction(CSC)is to detect and correct erroneous characters in Chinese text,which can result from various factors,such as inaccuracies in pinyin representation,character resemblance,and semantic discrepancies.However,existing methods often struggle to fully address these types of errors,impacting the overall correction accuracy.This paper introduces a multi-modal feature encoder designed to efficiently extract features from three distinct modalities:pinyin,semantics,and character morphology.Unlike previous methods that rely on direct fusion or fixed-weight summation to integrate multi-modal information,our approach employs a multi-head attention mechanism to focuse more on relevant modal information while dis-regarding less pertinent data.To prevent issues such as gradient explosion or vanishing,the model incorporates a residual connection of the original text vector for fine-tuning.This approach ensures robust model performance by maintaining essential linguistic details throughout the correction process.Experimental evaluations on the SIGHAN benchmark dataset demonstrate that the pro-posed model outperforms baseline approaches across various metrics and datasets,confirming its effectiveness and feasibility.展开更多
基金National Natural Science Foundation of China (52075420)Fundamental Research Funds for the Central Universities (xzy022023049)National Key Research and Development Program of China (2023YFB3408600)。
文摘The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational performance. Despite numerous data-driven methods reported in existing research for battery SOH estimation, these methods often exhibit inconsistent performance across different application scenarios. To address this issue and overcome the performance limitations of individual data-driven models,integrating multiple models for SOH estimation has received considerable attention. Ensemble learning(EL) typically leverages the strengths of multiple base models to achieve more robust and accurate outputs. However, the lack of a clear review of current research hinders the further development of ensemble methods in SOH estimation. Therefore, this paper comprehensively reviews multi-model ensemble learning methods for battery SOH estimation. First, existing ensemble methods are systematically categorized into 6 classes based on their combination strategies. Different realizations and underlying connections are meticulously analyzed for each category of EL methods, highlighting distinctions, innovations, and typical applications. Subsequently, these ensemble methods are comprehensively compared in terms of base models, combination strategies, and publication trends. Evaluations across 6 dimensions underscore the outstanding performance of stacking-based ensemble methods. Following this, these ensemble methods are further inspected from the perspectives of weighted ensemble and diversity, aiming to inspire potential approaches for enhancing ensemble performance. Moreover, addressing challenges such as base model selection, measuring model robustness and uncertainty, and interpretability of ensemble models in practical applications is emphasized. Finally, future research prospects are outlined, specifically noting that deep learning ensemble is poised to advance ensemble methods for battery SOH estimation. The convergence of advanced machine learning with ensemble learning is anticipated to yield valuable avenues for research. Accelerated research in ensemble learning holds promising prospects for achieving more accurate and reliable battery SOH estimation under real-world conditions.
基金The fund from Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)under contract No.SML2021SP310the National Natural Science Foundation of China under contract Nos 42227901 and 42475061the Key R&D Program of Zhejiang Province under contract No.2024C03257.
文摘In this study,we conducted an experiment to construct multi-model ensemble(MME)predictions for the El Niño-Southern Oscillation(ENSO)using a neural network,based on hindcast data released from five coupled oceanatmosphere models,which exhibit varying levels of complexity.This nonlinear approach demonstrated extraordinary superiority and effectiveness in constructing ENSO MME.Subsequently,we employed the leave-one-out crossvalidation and the moving base methods to further validate the robustness of the neural network model in the formulation of ENSO MME.In conclusion,the neural network algorithm outperforms the conventional approach of assigning a uniform weight to all models.This is evidenced by an enhancement in correlation coefficients and reduction in prediction errors,which have the potential to provide a more accurate ENSO forecast.
基金supported by General Scientific Research Funding of the Science and Technology Development Fund(FDCT)in Macao(No.0150/2022/A)the Faculty Research Grants of Macao University of Science and Technology(No.FRG-22-074-FIE).
文摘With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration prediction system is of great scientific and practical significance for accurate and reliable predictions.This paper proposes a combination of pointinterval prediction system for pollutant concentration prediction by leveraging neural network,meta-heuristic optimization algorithm,and fuzzy theory.Fuzzy information granulation technology is used in data preprocessing to transform numerical sequences into fuzzy particles for comprehensive feature extraction.The golden Jackal optimization algorithm is employed in the optimization stage to fine-tune model hyperparameters.In the prediction stage,an ensemble learning method combines training results frommultiplemodels to obtain final point predictions while also utilizing quantile regression and kernel density estimation methods for interval predictions on the test set.Experimental results demonstrate that the combined model achieves a high goodness of fit coefficient of determination(R^(2))at 99.3% and a maximum difference between prediction accuracy mean absolute percentage error(MAPE)and benchmark model at 12.6%.This suggests that the integrated learning system proposed in this paper can provide more accurate deterministic predictions as well as reliable uncertainty analysis compared to traditionalmodels,offering practical reference for air quality early warning.
基金the University of Transport Technology under the project entitled“Application of Machine Learning Algorithms in Landslide Susceptibility Mapping in Mountainous Areas”with grant number DTTD2022-16.
文摘This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble learning techniques:DAGGING(DG),MULTIBOOST(MB),and ADABOOST(AB).This combination resulted in three distinct ensemble models:DG-RBFN,MB-RBFN,and AB-RBFN.Additionally,a traditional weighted method,Information Value(IV),and a benchmark machine learning(ML)model,Multilayer Perceptron Neural Network(MLP),were employed for comparison and validation.The models were developed using ten landslide conditioning factors,which included slope,aspect,elevation,curvature,land cover,geomorphology,overburden depth,lithology,distance to rivers and distance to roads.These factors were instrumental in predicting the output variable,which was the probability of landslide occurrence.Statistical analysis of the models’performance indicated that the DG-RBFN model,with an Area Under ROC Curve(AUC)of 0.931,outperformed the other models.The AB-RBFN model achieved an AUC of 0.929,the MB-RBFN model had an AUC of 0.913,and the MLP model recorded an AUC of 0.926.These results suggest that the advanced ensemble ML model DG-RBFN was more accurate than traditional statistical model,single MLP model,and other ensemble models in preparing trustworthy landslide susceptibility maps,thereby enhancing land use planning and decision-making.
基金Construction Program of the Key Discipline of State Administration of Traditional Chinese Medicine of China(ZYYZDXK-2023069)Research Project of Shanghai Municipal Health Commission (2024QN018)Shanghai University of Traditional Chinese Medicine Science and Technology Development Program (23KFL005)。
文摘Objective To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data.Methods Clinical indicators,echocardiographic data,traditional Chinese medicine(TCM)tongue manifestations,and facial features were collected from patients who underwent coro-nary computed tomography angiography(CTA)in the Cardiac Care Unit(CCU)of Shanghai Tenth People's Hospital between May 1,2023 and May 1,2024.An adaptive weighted multi-modal data fusion(AWMDF)model based on deep learning was constructed to predict the severity of coronary artery stenosis.The model was evaluated using metrics including accura-cy,precision,recall,F1 score,and the area under the receiver operating characteristic(ROC)curve(AUC).Further performance assessment was conducted through comparisons with six ensemble machine learning methods,data ablation,model component ablation,and various decision-level fusion strategies.Results A total of 158 patients were included in the study.The AWMDF model achieved ex-cellent predictive performance(AUC=0.973,accuracy=0.937,precision=0.937,recall=0.929,and F1 score=0.933).Compared with model ablation,data ablation experiments,and various traditional machine learning models,the AWMDF model demonstrated superior per-formance.Moreover,the adaptive weighting strategy outperformed alternative approaches,including simple weighting,averaging,voting,and fixed-weight schemes.Conclusion The AWMDF model demonstrates potential clinical value in the non-invasive prediction of coronary artery disease and could serve as a tool for clinical decision support.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(NRF-2022R1I1A3063493).
文摘Smart manufacturing and Industry 4.0 are transforming traditional manufacturing processes by utilizing innovative technologies such as the artificial intelligence(AI)and internet of things(IoT)to enhance efficiency,reduce costs,and ensure product quality.In light of the recent advancement of Industry 4.0,identifying defects has become important for ensuring the quality of products during the manufacturing process.In this research,we present an ensemble methodology for accurately classifying hot rolled steel surface defects by combining the strengths of four pre-trained convolutional neural network(CNN)architectures:VGG16,VGG19,Xception,and Mobile-Net V2,compensating for their individual weaknesses.We evaluated our methodology on the Xsteel surface defect dataset(XSDD),which comprises seven different classes.The ensemble methodology integrated the predictions of individual models through two methods:model averaging and weighted averaging.Our evaluation showed that the model averaging ensemble achieved an accuracy of 98.89%,a recall of 98.92%,a precision of 99.05%,and an F1-score of 98.97%,while the weighted averaging ensemble reached an accuracy of 99.72%,a recall of 99.74%,a precision of 99.67%,and an F1-score of 99.70%.The proposed weighted averaging ensemble model outperformed the model averaging method and the individual models in detecting defects in terms of accuracy,recall,precision,and F1-score.Comparative analysis with recent studies also showed the superior performance of our methodology.
基金supported by the National Natural Science Foundation of China(22379021 and 22479021)。
文摘As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigation of degradation mechanisms.However,dynamic operating conditions,cell-to-cell inconsistencies,and limited availability of labeled data have posed significant challenges to accurate and robust prognosis and diagnosis.Herein,we introduce a time-series-decomposition-based ensembled lightweight learning model(TELL-Me),which employs a synergistic dual-module framework to facilitate accurate and reliable forecasting.The feature module formulates features with physical implications and sheds light on battery aging mechanisms,while the gradient module monitors capacity degradation rates and captures aging trend.TELL-Me achieves high accuracy in end-of-life prediction using minimal historical data from a single battery without requiring offline training dataset,and demonstrates impressive generality and robustness across various operating conditions and battery types.Additionally,by correlating feature contributions with degradation mechanisms across different datasets,TELL-Me is endowed with the diagnostic ability that not only enhances prediction reliability but also provides critical insights into the design and optimization of next-generation batteries.
基金National Natural Science Foundation of China,No.42271037Key Research and Development Program Project of Anhui Province,No.2022m07020011+1 种基金The University Synergy Innovation Program of Anhui Province,No.GXXT-2021-048Science Foundation for Excellent Young Scholars of Anhui,No.2108085Y13。
文摘Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning(ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following:(1) The stacking ensemble learning, using RF-XGBCB-LR model, significantly enhances flood susceptibility simulation.(2) In addition to rainfall,key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland.(3) In the northeast of the study area,heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management.
文摘Small-drone technology has opened a range of new applications for aerial transportation. These drones leverage the Internet of Things (IoT) to offer cross-location services for navigation. However, they are susceptible to security and privacy threats due to hardware and architectural issues. Although small drones hold promise for expansion in both civil and defense sectors, they have safety, security, and privacy threats. Addressing these challenges is crucial to maintaining the security and uninterrupted operations of these drones. In this regard, this study investigates security, and preservation concerning both the drones and Internet of Drones (IoD), emphasizing the significance of creating drone networks that are secure and can robustly withstand interceptions and intrusions. The proposed framework incorporates a weighted voting ensemble model comprising three convolutional neural network (CNN) models to enhance intrusion detection within the network. The employed CNNs are customized 1D models optimized to obtain better performance. The output from these CNNs is voted using a weighted criterion using a 0.4, 0.3, and 0.3 ratio for three CNNs, respectively. Experiments involve using multiple benchmark datasets, achieving an impressive accuracy of up to 99.89% on drone data. The proposed model shows promising results concerning precision, recall, and F1 as indicated by their obtained values of 99.92%, 99.98%, and 99.97%, respectively. Furthermore, cross-validation and performance comparison with existing works is also carried out. Findings indicate that the proposed approach offers a prospective solution for detecting security threats for aerial systems and satellite systems with high accuracy.
基金supported by the NSFC(12171038)and 985 Projects。
文摘In this paper,we consider the Fisher informations among three classical type β-ensembles when β>0 scales with n satisfying lim βn=∞.We offer the exact order of-the corresponding two Fisher informations,which indicates that theβ-Laguerre ensembles do not satisfy the logarithmic Sobolev inequality.We also give some limit theorems on the extremals of β-Jacobi ensembles for β>0 fixed.
基金funded by Research Project,grant number BHQ090003000X03.
文摘Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or obtaining entity related external knowledge from knowledge bases or Large Language Models(LLMs).However,these approaches ignore the poor semantic correlation between visual and textual modalities in MNER datasets and do not explore different multi-modal fusion approaches.In this paper,we present MMAVK,a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion,which aims to leverage the Multi-modal Large Language Model(MLLM)as an implicit knowledge base.It also extracts vision-based auxiliary knowledge from the image formore accurate and effective recognition.Specifically,we propose vision-based auxiliary knowledge generation,which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts,thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs.Furthermore,we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformerbased encoder.Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNER datasets,even when the largemodels employed have significantly fewer parameters than other baselines.
基金funded by Research Project,grant number BHQ090003000X03。
文摘Multi-modal knowledge graph completion(MMKGC)aims to complete missing entities or relations in multi-modal knowledge graphs,thereby discovering more previously unknown triples.Due to the continuous growth of data and knowledge and the limitations of data sources,the visual knowledge within the knowledge graphs is generally of low quality,and some entities suffer from the issue of missing visual modality.Nevertheless,previous studies of MMKGC have primarily focused on how to facilitate modality interaction and fusion while neglecting the problems of low modality quality and modality missing.In this case,mainstream MMKGC models only use pre-trained visual encoders to extract features and transfer the semantic information to the joint embeddings through modal fusion,which inevitably suffers from problems such as error propagation and increased uncertainty.To address these problems,we propose a Multi-modal knowledge graph Completion model based on Super-resolution and Detailed Description Generation(MMCSD).Specifically,we leverage a pre-trained residual network to enhance the resolution and improve the quality of the visual modality.Moreover,we design multi-level visual semantic extraction and entity description generation,thereby further extracting entity semantics from structural triples and visual images.Meanwhile,we train a variational multi-modal auto-encoder and utilize a pre-trained multi-modal language model to complement the missing visual features.We conducted experiments on FB15K-237 and DB13K,and the results showed that MMCSD can effectively perform MMKGC and achieve state-of-the-art performance.
基金supported by the Deanship of Research and Graduate Studies at King Khalid University under Small Research Project grant number RGP1/139/45.
文摘Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status.Each of these methods contributes unique diagnostic insights,enhancing the overall assessment of patient condition.Nevertheless,the amalgamation of data from multiple modalities presents difficulties due to disparities in resolution,data collection methods,and noise levels.While traditional models like Convolutional Neural Networks(CNNs)excel in single-modality tasks,they struggle to handle multi-modal complexities,lacking the capacity to model global relationships.This research presents a novel approach for examining multi-modal medical imagery using a transformer-based system.The framework employs self-attention and cross-attention mechanisms to synchronize and integrate features across various modalities.Additionally,it shows resilience to variations in noise and image quality,making it adaptable for real-time clinical use.To address the computational hurdles linked to transformer models,particularly in real-time clinical applications in resource-constrained environments,several optimization techniques have been integrated to boost scalability and efficiency.Initially,a streamlined transformer architecture was adopted to minimize the computational load while maintaining model effectiveness.Methods such as model pruning,quantization,and knowledge distillation have been applied to reduce the parameter count and enhance the inference speed.Furthermore,efficient attention mechanisms such as linear or sparse attention were employed to alleviate the substantial memory and processing requirements of traditional self-attention operations.For further deployment optimization,researchers have implemented hardware-aware acceleration strategies,including the use of TensorRT and ONNX-based model compression,to ensure efficient execution on edge devices.These optimizations allow the approach to function effectively in real-time clinical settings,ensuring viability even in environments with limited resources.Future research directions include integrating non-imaging data to facilitate personalized treatment and enhancing computational efficiency for implementation in resource-limited environments.This study highlights the transformative potential of transformer models in multi-modal medical imaging,offering improvements in diagnostic accuracy and patient care outcomes.
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partially supported by the National Natural Science Foundation of China under Grants 62471493 and 62402257(for conceptualization and investigation)partially supported by the Natural Science Foundation of Shandong Province,China under Grants ZR2023LZH017,ZR2024MF066,and 2023QF025(for formal analysis and validation)+1 种基金partially supported by the Open Foundation of Key Laboratory of Computing Power Network and Information Security,Ministry of Education,Qilu University of Technology(Shandong Academy of Sciences)under Grant 2023ZD010(for methodology and model design)partially supported by the Russian Science Foundation(RSF)Project under Grant 22-71-10095-P(for validation and results verification).
文摘To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.
文摘Traditional Chinese medicine(TCM)demonstrates distinctive advantages in disease prevention and treatment.However,analyzing its biological mechanisms through the modern medical research paradigm of“single drug,single target”presents significant challenges due to its holistic approach.Network pharmacology and its core theory of network targets connect drugs and diseases from a holistic and systematic perspective based on biological networks,overcoming the limitations of reductionist research models and showing considerable value in TCM research.Recent integration of network target computational and experimental methods with artificial intelligence(AI)and multi-modal multi-omics technologies has substantially enhanced network pharmacology methodology.The advancement in computational and experimental techniques provides complementary support for network target theory in decoding TCM principles.This review,centered on network targets,examines the progress of network target methods combined with AI in predicting disease molecular mechanisms and drug-target relationships,alongside the application of multi-modal multi-omics technologies in analyzing TCM formulae,syndromes,and toxicity.Looking forward,network target theory is expected to incorporate emerging technologies while developing novel approaches aligned with its unique characteristics,potentially leading to significant breakthroughs in TCM research and advancing scientific understanding and innovation in TCM.
基金funded by the Yangtze River Delta Science and Technology Innovation Community Joint Research Project(2023CSJGG1600)the Natural Science Foundation of Anhui Province(2208085MF173)Wuhu“ChiZhu Light”Major Science and Technology Project(2023ZD01,2023ZD03).
文摘As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.
基金Supported by the National Natural Science Foundation of China(No.61472256,61170277)the Hujiang Foundation(No.A14006).
文摘The primary objective of Chinese spelling correction(CSC)is to detect and correct erroneous characters in Chinese text,which can result from various factors,such as inaccuracies in pinyin representation,character resemblance,and semantic discrepancies.However,existing methods often struggle to fully address these types of errors,impacting the overall correction accuracy.This paper introduces a multi-modal feature encoder designed to efficiently extract features from three distinct modalities:pinyin,semantics,and character morphology.Unlike previous methods that rely on direct fusion or fixed-weight summation to integrate multi-modal information,our approach employs a multi-head attention mechanism to focuse more on relevant modal information while dis-regarding less pertinent data.To prevent issues such as gradient explosion or vanishing,the model incorporates a residual connection of the original text vector for fine-tuning.This approach ensures robust model performance by maintaining essential linguistic details throughout the correction process.Experimental evaluations on the SIGHAN benchmark dataset demonstrate that the pro-posed model outperforms baseline approaches across various metrics and datasets,confirming its effectiveness and feasibility.
