This paper aims to develop Machine Learning algorithms to classify electronic articles related to this phenomenon by retrieving information and topic modelling.The Methodology of this study is categorized into three p...This paper aims to develop Machine Learning algorithms to classify electronic articles related to this phenomenon by retrieving information and topic modelling.The Methodology of this study is categorized into three phases:the Text Classification Approach(TCA),the Proposed Algorithms Interpretation(PAI),andfinally,Information Retrieval Approach(IRA).The TCA reflects the text preprocessing pipeline called a clean corpus.The Global Vec-tors for Word Representation(Glove)pre-trained model,FastText,Term Frequency-Inverse Document Fre-quency(TF-IDF),and Bag-of-Words(BOW)for extracting the features have been interpreted in this research.The PAI manifests the Bidirectional Long Short-Term Memory(Bi-LSTM)and Convolutional Neural Network(CNN)to classify the COVID-19 news.Again,the IRA explains the mathematical interpretation of Latent Dirich-let Allocation(LDA),obtained for modelling the topic of Information Retrieval(IR).In this study,99%accuracy was obtained by performing K-fold cross-validation on Bi-LSTM with Glove.A comparative analysis between Deep Learning and Machine Learning based on feature extraction and computational complexity exploration has been performed in this research.Furthermore,some text analyses and the most influential aspects of each document have been explored in this study.We have utilized Bidirectional Encoder Representations from Trans-formers(BERT)as a Deep Learning mechanism in our model training,but the result has not been uncovered satisfactory.However,the proposed system can be adjustable in the real-time news classification of COVID-19.展开更多
An effective and reliable prediction of the remaining useful life(RUL)of a tool is important to a metal forming process because it can significantly reduce unexpected maintenance,avoid machine shutdowns and increase s...An effective and reliable prediction of the remaining useful life(RUL)of a tool is important to a metal forming process because it can significantly reduce unexpected maintenance,avoid machine shutdowns and increase system stability.This study proposes a new data-driven approach to the RUL prediction for metal forming processes under multiple contact sliding conditions.The data-driven approach took advantage of bidirectional long short-term memory(BLSTM)and convolutional neural networks(CNN).A pre-trained lightweight CNN-based network,WearNet,was re-trained to classify the wear states of workpiece surfaces with a high accuracy,then the classification results were passed into a BLSTM-based regression model as inputs for RUL estimation.The experimental results demonstrated that this approach was able to predict the RUL values with a small error(below 5%)and a low root mean square error(RMSE)(around 1.5),which was more superior and robust than the other state-of-the-art methods.展开更多
The COVID-19 pandemic has significantly impacted global health,social,and economic situations since its emergence in December 2019.The primary focus of this study is to propose a distinct vaccination policy and assess...The COVID-19 pandemic has significantly impacted global health,social,and economic situations since its emergence in December 2019.The primary focus of this study is to propose a distinct vaccination policy and assess its impact on controlling COVID-19 transmission in Malaysia using a Bayesian data-driven approach,concentrating on the year 2021.We employ a compartmental Susceptible-Exposed-Infected-Recovered-Vaccinated(SEIRV)model,incorporating a time-varying transmission rate and a data-driven method for its estimation through an Exploratory Data Analysis(EDA)approach.While no vaccine guarantees total immunity against the disease,and vaccine immunity wanes over time,it is critical to include and accurately estimate vaccine efficacy,as well as a constant vaccine immunity decay or wane factor,to better simulate the dynamics of vaccine-induced protection over time.Based on the distribution and effectiveness of vaccines,we integrated a data-driven estimation of vaccine efficacy,calculated at 75%for Malaysia,underscoring the model's realism and relevance to the specific context of the country.The Bayesian inference framework is used to assimilate various data sources and account for underlying uncertainties in model parameters.The model is fitted to real-world data from Malaysia to analyze disease spread trends and evaluate the effectiveness of our proposed vaccination policy.Our findings reveal that this distinct vaccination policy,which emphasizes an accelerated vaccination rate during the initial stages of the program,is highly effective in mitigating the spread of COVID-19 and substantially reducing the pandemic peak and new infections.The study found that vaccinating 57–66%of the population(as opposed to 76%in the real data)with a better vaccination policy such as proposed here is able to significantly reduce the number of new infections and ultimately reduce the costs associated with new infections.The study contributes to the development of a robust and informative representation of COVID-19 transmission and vaccination,offering valuable insights for policymakers on the potential benefits and limitations of different vaccination policies,particularly highlighting the importance of a well-planned and efficient vaccination rollout strategy.While the methodology used in this study is specifically applied to national data from Malaysia,its successful application to local regions within Malaysia,such as Selangor and Johor,indicates its adaptability and potential for broader application.This demonstrates the model's adaptability for policy assessment and improvement across various demographic and epidemiological landscapes,implying its usefulness for similar datasets from various geographical regions.展开更多
Numerous influence factors will lead to the inaccurate prediction of fatigue crack propagation(FCP)life of the metal structure based on the existing FCP model,while the prediction method based on machine learning(ML)a...Numerous influence factors will lead to the inaccurate prediction of fatigue crack propagation(FCP)life of the metal structure based on the existing FCP model,while the prediction method based on machine learning(ML)and data-driven approach can provide a new idea for accurately predicting the FCP life of the metal structure.In response to the inconvenience of the online prediction method and the inaccu-racy of the offline prediction method,an improved offline prediction method based on data feedback is presented in this paper.FCP tests of reduced scale models of balcony opening corners in a cruise ship are conducted to obtain experimental data with respect to the a-N curves.The crack length corresponding to the cycle is trained using a support vector regression(SVR)and back propagation neural network(BP NN)algorithms.FCP prediction lives of test specimens are performed according to the online,offline,and improved offline prediction methods.Effects of the number of feedback data,the sequence length(SL)in the input set,and the cycle interval on prediction accuracy are discussed.The generalization ability of the proposed method is validated by comparing the prediction results with the experimental data in the literature.The larger the number of feedback data,the higher the prediction accuracy.The results show that 1/5 and 1/2 feedback data are needed in the SVR and BP NN algorithm with SL is 5,respectively.Furthermore,the SVR algorithm and SL=5 are recommended for FCP life prediction using the improved offline prediction method.展开更多
The electricity and steam integrated energy systems,which can capture waste heat and improve the overall energy efficiency,have been widely utilised in industrial parks.However,intensive and frequent changes in demand...The electricity and steam integrated energy systems,which can capture waste heat and improve the overall energy efficiency,have been widely utilised in industrial parks.However,intensive and frequent changes in demands would lead to model parameters with strong time-varying characteristics.This paper proposes a hybrid physics and data-driven framework for online joint state and parameter estimation of steam and electricity integrated energy system.Based on the physical non-linear state space models for the electricity network(EN)and steam heating network(SHN),relevance vector machine is developed to learn parameters'dynamic characteristics with respect to model states,which is embedded with physical models.Then,the online joint state and parameter estimation based on unscented Kalman filter is proposed,which would be learnt recursively to capture the spatiotemporal transient characteristics between electricity and SHNs.The IEEE 39-bus EN and the 29-nodes SHN are employed to verify the effectiveness of the proposed method.The experimental results validate that the pro-posed method can provide a higher estimation accuracy than the state-of-the-art approaches.展开更多
The progressive loss of dopaminergic neurons in affected patient brains is one of the pathological features of Parkinson's disease,the second most common human neurodegenerative disease.Although the detailed patho...The progressive loss of dopaminergic neurons in affected patient brains is one of the pathological features of Parkinson's disease,the second most common human neurodegenerative disease.Although the detailed pathogenesis accounting for dopaminergic neuron degeneration in Parkinson's disease is still unclear,the advancement of stem cell approaches has shown promise for Parkinson's disease research and therapy.The induced pluripotent stem cells have been commonly used to generate dopaminergic neurons,which has provided valuable insights to improve our understanding of Parkinson's disease pathogenesis and contributed to anti-Parkinson's disease therapies.The current review discusses the practical approaches and potential applications of induced pluripotent stem cell techniques for generating and differentiating dopaminergic neurons from induced pluripotent stem cells.The benefits of induced pluripotent stem cell-based research are highlighted.Various dopaminergic neuron differentiation protocols from induced pluripotent stem cells are compared.The emerging three-dimension-based brain organoid models compared with conventional two-dimensional cell culture are evaluated.Finally,limitations,challenges,and future directions of induced pluripotent stem cell–based approaches are analyzed and proposed,which will be significant to the future application of induced pluripotent stem cell-related techniques for Parkinson's disease.展开更多
This article provides a comprehensive analysis of the study by Hou et al,focusing on the complex interplay between psychological and physical factors in the postoperative recovery(POR)of patients with perianal disease...This article provides a comprehensive analysis of the study by Hou et al,focusing on the complex interplay between psychological and physical factors in the postoperative recovery(POR)of patients with perianal diseases.The study sheds light on how illness perception,anxiety,and depression significantly influence recovery outcomes.Hou et al developed a predictive model that demonstrated high accuracy in identifying patients at risk of poor recovery.The article explores the critical role of pre-operative psychological assessment,highlighting the need for mental health support and personalized recovery plans in enhancing POR quality.A multidisciplinary approach,integrating mental health professionals with surgeons,anesthesiologists,and other specialists,is emphasized to ensure comprehensive care for patients.The study’s findings serve as a call to integrate psychological care into surgical practice to optimize outcomes for patients with perianal diseases.展开更多
Objective: To explore the effect of Health Action Process Approach (HAPA) theory in patients with type D personality psoriasis. Methods: A total of 66 patients with type D personality psoriasis admitted to the dermato...Objective: To explore the effect of Health Action Process Approach (HAPA) theory in patients with type D personality psoriasis. Methods: A total of 66 patients with type D personality psoriasis admitted to the dermatology department of a top-three hospital in Jingzhou City from November 2022 to July 2023 were selected and divided into control group and test group with 33 cases in each group by random number table method. The control group received routine health education, and the experimental group received health education based on the HAPA theory. Chronic disease self-efficacy scale, hospital anxiety and depression scale and skin disease quality of life scale were used to evaluate the effect of intervention. Results: After 3 months of intervention, the scores of self-efficacy in experimental group were higher than those in control group (P P Conclusion: Health education based on the theory of HAPA can enhance the self-efficacy of patients with type D personality psoriasis, relieve negative emotions and improve their quality of life.展开更多
When assessing seismic liquefaction potential with data-driven models,addressing the uncertainties of establishing models,interpreting cone penetration tests(CPT)data and decision threshold is crucial for avoiding bia...When assessing seismic liquefaction potential with data-driven models,addressing the uncertainties of establishing models,interpreting cone penetration tests(CPT)data and decision threshold is crucial for avoiding biased data selection,ameliorating overconfident models,and being flexible to varying practical objectives,especially when the training and testing data are not identically distributed.A workflow characterized by leveraging Bayesian methodology was proposed to address these issues.Employing a Multi-Layer Perceptron(MLP)as the foundational model,this approach was benchmarked against empirical methods and advanced algorithms for its efficacy in simplicity,accuracy,and resistance to overfitting.The analysis revealed that,while MLP models optimized via maximum a posteriori algorithm suffices for straightforward scenarios,Bayesian neural networks showed great potential for preventing overfitting.Additionally,integrating decision thresholds through various evaluative principles offers insights for challenging decisions.Two case studies demonstrate the framework's capacity for nuanced interpretation of in situ data,employing a model committee for a detailed evaluation of liquefaction potential via Monte Carlo simulations and basic statistics.Overall,the proposed step-by-step workflow for analyzing seismic liquefaction incorporates multifold testing and real-world data validation,showing improved robustness against overfitting and greater versatility in addressing practical challenges.This research contributes to the seismic liquefaction assessment field by providing a structured,adaptable methodology for accurate and reliable analysis.展开更多
With the rapid advancement of machine learning technology and its growing adoption in research and engineering applications,an increasing number of studies have embraced data-driven approaches for modeling wind turbin...With the rapid advancement of machine learning technology and its growing adoption in research and engineering applications,an increasing number of studies have embraced data-driven approaches for modeling wind turbine wakes.These models leverage the ability to capture complex,high-dimensional characteristics of wind turbine wakes while offering significantly greater efficiency in the prediction process than physics-driven models.As a result,data-driven wind turbine wake models are regarded as powerful and effective tools for predicting wake behavior and turbine power output.This paper aims to provide a concise yet comprehensive review of existing studies on wind turbine wake modeling that employ data-driven approaches.It begins by defining and classifying machine learning methods to facilitate a clearer understanding of the reviewed literature.Subsequently,the related studies are categorized into four key areas:wind turbine power prediction,data-driven analytic wake models,wake field reconstruction,and the incorporation of explicit physical constraints.The accuracy of data-driven models is influenced by two primary factors:the quality of the training data and the performance of the model itself.Accordingly,both data accuracy and model structure are discussed in detail within the review.展开更多
BACKGROUND The root of mesentery dissection is one of the critical maneuvers,especially in borderline resectable pancreatic head cancer.Intra-abdominal chyle leak(CL)including chylous ascites may ensue in up to 10%of ...BACKGROUND The root of mesentery dissection is one of the critical maneuvers,especially in borderline resectable pancreatic head cancer.Intra-abdominal chyle leak(CL)including chylous ascites may ensue in up to 10%of patients after pancreatic resections.Globally recognized superior mesenteric artery(SMA)first approaches are invariably performed.The mesenteric dissection through the inferior infracolic approach has been discussed in this study emphasizing its post-operative impact on CL which is the cornerstone of this study.AIM To assess incidence,risk factors,clinical impact of CL following root of mesentery dissection,and the different treatment modalities.METHODS This is a retrospective study incorporating the patients who underwent dissection of the root of mesentery with inferior infracolic SMA first approach pancreat-oduodenectomy for the ventral body and uncinate mass of pancreas in the Department of Gastrointestinal and General Surgery of Kathmandu Medical College and Teaching Hospital from January 1,2021 to February 28,2024.Intraop-erative findings and postoperative outcomes were analyzed.RESULTS In three years,ten patients underwent root of mesentery dissection with inferior infracolic SMA first approach pancreatoduodenectomy.The mean age was 67.6 years with a male-to-female ratio of 4:5.CL was seen in four patients.With virtue of CL,Clavien-Dindo grade Ⅱ or higher morbidity was observed in four patients.Two patients had a hospital stay of more than 20 days with the former having a delayed gastric emptying and the latter with long-term total parenteral nutrition requirement.The mean operative time was 330 minutes.Curative resection was achieved in 100%of the patients.The mean duration of the intensive care unit and hospital stay were 2.55±1.45 days and 15.7±5.32 days,respectively.CONCLUSION Root of mesentery dissection with lymphadenectomy and vascular resection correlated with occurrence of CL.After complete curative resection,these were managed with total parenteral nutrition without adversely impacting outcome.展开更多
Background:Dorsal approach is the potentially effective strategy for minimally invasive liver resection.This study aimed to compare the outcomes between robot-assisted and laparoscopic hemihepatectomy through dorsal a...Background:Dorsal approach is the potentially effective strategy for minimally invasive liver resection.This study aimed to compare the outcomes between robot-assisted and laparoscopic hemihepatectomy through dorsal approach.Methods:We compared the patients who underwent robot-assisted hemihepatectomy(Rob-HH)and who had laparoscopic hemihepatectomy(Lap-HH)through dorsal approach between January 2020 and December 2022.A 1:1 propensity score-matching(PSM)analysis was performed to minimize bias and confounding factors.Results:Ninety-six patients were included,41 with Rob-HH and 55 with Lap-HH.Among them,58 underwent left hemihepatectomy(LHH)and 38 underwent right hemihepatectomy(RHH).Compared with LapHH group,patients with Rob-HH had less estimated blood loss(median:100.0 vs.300.0 m L,P=0.016),lower blood transfusion rates(4.9%vs.29.1%,P=0.003)and postoperative complication rates(26.8%vs.54.5%,P=0.016).These significant differences consistently existed after PSM and in the LHH subgroups.Furthermore,robot-assisted LHH was associated with decreased Pringle duration(45 vs.60 min,P=0.047).RHH subgroup analysis showed that compared with Lap-RHH,Rob-RHH was associated with less estimated blood loss(200.0 vs.400.0 m L,P=0.013).No significant differences were found in other perioperative outcomes among pre-and post-PSM cohorts,such as Pringle duration,operative time,and hospital stay.Conclusions:The dorsal approach was a safe and feasible strategy for hemi-hepatectomy with favorable outcomes under robot-assisted system in reducing intraoperative blood loss,transfusion,and postoperative complications.展开更多
In recent years,the production-oriented approach has been applied in the field of teaching Chinese as a foreign language,providing a new perspective for language and cultural instruction.Currently,several issues exist...In recent years,the production-oriented approach has been applied in the field of teaching Chinese as a foreign language,providing a new perspective for language and cultural instruction.Currently,several issues exist in cultural teaching,such as the lack of in-depth cultural input,insufficient training in cross-cultural communication skills,and the over-stylization of cultural teaching in the classroom.The production-oriented approach offers a solution to these challenges.This paper seeks to introduce the production-oriented method into the teaching of Chinese culture as a foreign language,using silk culture as a case study for teaching design.The aim is to implement cultural teaching through a new instructional model and to promote the spread of Chinese silk culture.展开更多
In this article,the department of the author Joo-Ho Lee“Department of Surgery,Ewha Womans University Mokdong Hospital,Seoul 07985,Republic of Korea”was incorrectly listed.It has been updated as follows:Joo-Ho Lee.De...In this article,the department of the author Joo-Ho Lee“Department of Surgery,Ewha Womans University Mokdong Hospital,Seoul 07985,Republic of Korea”was incorrectly listed.It has been updated as follows:Joo-Ho Lee.Department of Surgery,Nowon Eulji Medical Center,Eulji University,Seoul 01830,Republic of Korea.展开更多
The rising prevalence of chronic multimorbidity poses substantial challenges to healthcare systems,necessitating the development of innovative management strategies to optimize patient care and system efficiency.The s...The rising prevalence of chronic multimorbidity poses substantial challenges to healthcare systems,necessitating the development of innovative management strategies to optimize patient care and system efficiency.The study by Fontalba-Navas et al investigates the implementation of a novel high complexity unit(HCU)specifically designed to improve the management of patients with chronic complex conditions.By adopting a multidisciplinary approach,the HCU aims to provide comprehensive,patient-centered care that enhances health outcomes and alleviates the strain on traditional hospital services.Utilizing a longitudinal analysis of data from the Basic Minimum Data Set,this study compares hospitalization metrics among the HCU,Internal Medicine,and other departments within a regional hospital throughout 2022.The findings reveal that the HCU's integrated care model significantly reduces readmission rates and boosts patient satisfaction compared to conventional care practices.The study highlights the HCU's potential as a replicable model for managing chronic multimorbidity,emphasizing its effectiveness in minimizing unnecessary hospitalizations and enhancing the overall quality of patient care.This innovative approach not only addresses the complexities associated with chronic multimorbid conditions but also offers a sustainable framework for healthcare systems confronting similar challenges.展开更多
Electronic circular dichroism(ECD)spectrum is an important tool for as-sessing molecular chirality.Tradition-al methods,like linear response time-dependent density functional theory(LR-TDDFT),predict ECD spectra well ...Electronic circular dichroism(ECD)spectrum is an important tool for as-sessing molecular chirality.Tradition-al methods,like linear response time-dependent density functional theory(LR-TDDFT),predict ECD spectra well for small or medium-sized molecules,but struggle with large sys-tems due to high computational costs,making it a significant challenge to ac-curately and efficiently predict the ECD properties of complex systems.Within the framework of the generalized energy-based fragmentation(GEBF)method for localized excited states(ESs)calculation,we propose a combination algorithm for calculating rotatory strengths of ESs in condensed phase systems.This algorithm estimates the rotatory strength of the total system by calculating and combin-ing the transition electric and magnetic dipole moments of subsystems.We have used the GEBF method to calculate the ECD properties of chiral drug molecule derivatives,green fluo-rescent protein,and cyclodextrin derivatives,and compared their results with traditional methods or experimental data.The results show that this method can efficiently and accu-rately predict the ECD spectra of these systems.Thus,the GEBF method for ECD spectra demonstrates great potential in the chiral analysis of complex systems and chiral material design,promising to become a powerful theoretical tool in chiral chemistry.展开更多
In situ recycling is one of the most effective methods to dispose of earth pressure balance(EPB)shield waste muck with residual foaming agents with high moisture content.In this context,response surface methodology(RS...In situ recycling is one of the most effective methods to dispose of earth pressure balance(EPB)shield waste muck with residual foaming agents with high moisture content.In this context,response surface methodology(RSM)was employed to quantify the effects of independent variables,including flocculant dosage,defoamer dosage,and muck drying mass(MDM)and their interactions on defoaming-flocculation-dewatering indices.The polymeric aluminum chloride(PACL)and hydroxy silicone oil-glycerol polypropylene ether(H-G)were selected as the flocculant and defoamer.The contents of surfactants and foam stabilizers in residual foaming agents were determined using the proposed empirical equation.The defoaming ratio,antifoaming ratio,turbidity,moisture content,filtration loss ratio,and fall cone penetration depth were considered as dependent variables.The accuracy of developed RSM models was verified by the analysis results of variance,residuals,and paired t-test.Combined with the desirability approach,an optimal mixing ratio of 0.078 wt%PACL,0.016 wt%H-G,and 27.882 wt%MDM was recommended,leading to a defoaming ratio of 98.34 vol%for residual foams and a moisture content of 56.72 wt%for pressure-filtration cakes.Our findings were demonstrated to be able to provide useful guidance for prediction and optimization of the in situ recycling indicators of EPB shield waste muck in metro tunnel construction sites.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
Microwave-assisted rock-breaking technology,as a novel hybrid approach,is anticipated to facilitate the efficient excavation of complex rock formations.It is therefore crucial to understand the damage and failure mech...Microwave-assisted rock-breaking technology,as a novel hybrid approach,is anticipated to facilitate the efficient excavation of complex rock formations.It is therefore crucial to understand the damage and failure mechanisms of rocks that have been subjected to irradiation.In this study,uniaxial compression experiments were conducted on granite specimens after 1.4 kW microwave irradiation for varying durations.Furthermore,a numerical method was proposed to solve electromagnetic-thermal-mechanical coupling problems by integrating finite and discrete elements.The results demonstrated a differential temperature distribution(high temperature in the middle and low-temperature areas at the ends)in the granite specimens under microwave irradiation,which resulted in a notable reduction in their physical and mechanical properties.As the duration of irradiation increased,the rate of heating and the extent of strength reduction both diminished,while the morphology and distribution of cracks at ultimate failure became increasingly complex.The numerical method effectively addresses the simulation challenges associated with the electromagnetic selective heating of granite containing multiple polar minerals under microwave irradiation.This approach accounted for the non-uniform thermal expansion of the minerals and provided a comprehensive model of damage progression under compression.展开更多
Lithium-ion batteries are the preferred green energy storage method and are equipped with intelligent battery management systems(BMSs)that efficiently manage the batteries.This not only ensures the safety performance ...Lithium-ion batteries are the preferred green energy storage method and are equipped with intelligent battery management systems(BMSs)that efficiently manage the batteries.This not only ensures the safety performance of the batteries but also significantly improves their efficiency and reduces their damage rate.Throughout their whole life cycle,lithium-ion batteries undergo aging and performance degradation due to diverse external environments and irregular degradation of internal materials.This degradation is reflected in the state of health(SOH)assessment.Therefore,this review offers the first comprehensive analysis of battery SOH estimation strategies across the entire lifecycle over the past five years,highlighting common research focuses rooted in data-driven methods.It delves into various dimensions such as dataset integration and preprocessing,health feature parameter extraction,and the construction of SOH estimation models.These approaches unearth hidden insights within data,addressing the inherent tension between computational complexity and estimation accuracy.To enha nce support for in-vehicle implementation,cloud computing,and the echelon technologies of battery recycling,remanufacturing,and reuse,as well as to offer insights into these technologies,a segmented management approach will be introduced in the future.This will encompass source domain data processing,multi-feature factor reconfiguration,hybrid drive modeling,parameter correction mechanisms,and fulltime health management.Based on the best SOH estimation outcomes,health strategies tailored to different stages can be devised in the future,leading to the establishment of a comprehensive SOH assessment framework.This will mitigate cross-domain distribution disparities and facilitate adaptation to a broader array of dynamic operation protocols.This article reviews the current research landscape from four perspectives and discusses the challenges that lie ahead.Researchers and practitioners can gain a comprehensive understanding of battery SOH estimation methods,offering valuable insights for the development of advanced battery management systems and embedded application research.展开更多
文摘This paper aims to develop Machine Learning algorithms to classify electronic articles related to this phenomenon by retrieving information and topic modelling.The Methodology of this study is categorized into three phases:the Text Classification Approach(TCA),the Proposed Algorithms Interpretation(PAI),andfinally,Information Retrieval Approach(IRA).The TCA reflects the text preprocessing pipeline called a clean corpus.The Global Vec-tors for Word Representation(Glove)pre-trained model,FastText,Term Frequency-Inverse Document Fre-quency(TF-IDF),and Bag-of-Words(BOW)for extracting the features have been interpreted in this research.The PAI manifests the Bidirectional Long Short-Term Memory(Bi-LSTM)and Convolutional Neural Network(CNN)to classify the COVID-19 news.Again,the IRA explains the mathematical interpretation of Latent Dirich-let Allocation(LDA),obtained for modelling the topic of Information Retrieval(IR).In this study,99%accuracy was obtained by performing K-fold cross-validation on Bi-LSTM with Glove.A comparative analysis between Deep Learning and Machine Learning based on feature extraction and computational complexity exploration has been performed in this research.Furthermore,some text analyses and the most influential aspects of each document have been explored in this study.We have utilized Bidirectional Encoder Representations from Trans-formers(BERT)as a Deep Learning mechanism in our model training,but the result has not been uncovered satisfactory.However,the proposed system can be adjustable in the real-time news classification of COVID-19.
基金supported by the Baosteel Australia Research and Development Centre(BAJC)Portfolio(Grant No.BA17001)the ARC Hub for Computational Particle Technology(Grant No.IH140100035)+1 种基金the Chinese Guangdong Specific Discipline Project(Grant No.2020ZDZX2006)the Shenzhen Key Laboratory Project of Cross-scale Manufacturing Mechanics(Grant No.ZDSYS20200810171201007).
文摘An effective and reliable prediction of the remaining useful life(RUL)of a tool is important to a metal forming process because it can significantly reduce unexpected maintenance,avoid machine shutdowns and increase system stability.This study proposes a new data-driven approach to the RUL prediction for metal forming processes under multiple contact sliding conditions.The data-driven approach took advantage of bidirectional long short-term memory(BLSTM)and convolutional neural networks(CNN).A pre-trained lightweight CNN-based network,WearNet,was re-trained to classify the wear states of workpiece surfaces with a high accuracy,then the classification results were passed into a BLSTM-based regression model as inputs for RUL estimation.The experimental results demonstrated that this approach was able to predict the RUL values with a small error(below 5%)and a low root mean square error(RMSE)(around 1.5),which was more superior and robust than the other state-of-the-art methods.
基金his work was funded by the James Watt PhD Scholarship program supported by Heriot-Watt University.
文摘The COVID-19 pandemic has significantly impacted global health,social,and economic situations since its emergence in December 2019.The primary focus of this study is to propose a distinct vaccination policy and assess its impact on controlling COVID-19 transmission in Malaysia using a Bayesian data-driven approach,concentrating on the year 2021.We employ a compartmental Susceptible-Exposed-Infected-Recovered-Vaccinated(SEIRV)model,incorporating a time-varying transmission rate and a data-driven method for its estimation through an Exploratory Data Analysis(EDA)approach.While no vaccine guarantees total immunity against the disease,and vaccine immunity wanes over time,it is critical to include and accurately estimate vaccine efficacy,as well as a constant vaccine immunity decay or wane factor,to better simulate the dynamics of vaccine-induced protection over time.Based on the distribution and effectiveness of vaccines,we integrated a data-driven estimation of vaccine efficacy,calculated at 75%for Malaysia,underscoring the model's realism and relevance to the specific context of the country.The Bayesian inference framework is used to assimilate various data sources and account for underlying uncertainties in model parameters.The model is fitted to real-world data from Malaysia to analyze disease spread trends and evaluate the effectiveness of our proposed vaccination policy.Our findings reveal that this distinct vaccination policy,which emphasizes an accelerated vaccination rate during the initial stages of the program,is highly effective in mitigating the spread of COVID-19 and substantially reducing the pandemic peak and new infections.The study found that vaccinating 57–66%of the population(as opposed to 76%in the real data)with a better vaccination policy such as proposed here is able to significantly reduce the number of new infections and ultimately reduce the costs associated with new infections.The study contributes to the development of a robust and informative representation of COVID-19 transmission and vaccination,offering valuable insights for policymakers on the potential benefits and limitations of different vaccination policies,particularly highlighting the importance of a well-planned and efficient vaccination rollout strategy.While the methodology used in this study is specifically applied to national data from Malaysia,its successful application to local regions within Malaysia,such as Selangor and Johor,indicates its adaptability and potential for broader application.This demonstrates the model's adaptability for policy assessment and improvement across various demographic and epidemiological landscapes,implying its usefulness for similar datasets from various geographical regions.
文摘Numerous influence factors will lead to the inaccurate prediction of fatigue crack propagation(FCP)life of the metal structure based on the existing FCP model,while the prediction method based on machine learning(ML)and data-driven approach can provide a new idea for accurately predicting the FCP life of the metal structure.In response to the inconvenience of the online prediction method and the inaccu-racy of the offline prediction method,an improved offline prediction method based on data feedback is presented in this paper.FCP tests of reduced scale models of balcony opening corners in a cruise ship are conducted to obtain experimental data with respect to the a-N curves.The crack length corresponding to the cycle is trained using a support vector regression(SVR)and back propagation neural network(BP NN)algorithms.FCP prediction lives of test specimens are performed according to the online,offline,and improved offline prediction methods.Effects of the number of feedback data,the sequence length(SL)in the input set,and the cycle interval on prediction accuracy are discussed.The generalization ability of the proposed method is validated by comparing the prediction results with the experimental data in the literature.The larger the number of feedback data,the higher the prediction accuracy.The results show that 1/5 and 1/2 feedback data are needed in the SVR and BP NN algorithm with SL is 5,respectively.Furthermore,the SVR algorithm and SL=5 are recommended for FCP life prediction using the improved offline prediction method.
基金National Natural Sciences Foundation of China,Grant/Award Numbers:62125302,62203087Sci-Tech Talent Innovation Support Program of Dalian,Grant/Award Number:2022RG03+1 种基金Liaoning Revitalization Talents Program,Grant/Award Number:XLYC2002087Young Elite Scientist Sponsorship Program by CAST,Grant/Award Number:YESS20220018。
文摘The electricity and steam integrated energy systems,which can capture waste heat and improve the overall energy efficiency,have been widely utilised in industrial parks.However,intensive and frequent changes in demands would lead to model parameters with strong time-varying characteristics.This paper proposes a hybrid physics and data-driven framework for online joint state and parameter estimation of steam and electricity integrated energy system.Based on the physical non-linear state space models for the electricity network(EN)and steam heating network(SHN),relevance vector machine is developed to learn parameters'dynamic characteristics with respect to model states,which is embedded with physical models.Then,the online joint state and parameter estimation based on unscented Kalman filter is proposed,which would be learnt recursively to capture the spatiotemporal transient characteristics between electricity and SHNs.The IEEE 39-bus EN and the 29-nodes SHN are employed to verify the effectiveness of the proposed method.The experimental results validate that the pro-posed method can provide a higher estimation accuracy than the state-of-the-art approaches.
基金supported by Singapore National Medical Research Council(NMRC)grants,including CS-IRG,HLCA2022(to ZDZ),STaR,OF LCG 000207(to EKT)a Clinical Translational Research Programme in Parkinson's DiseaseDuke-Duke-NUS collaboration pilot grant(to ZDZ)。
文摘The progressive loss of dopaminergic neurons in affected patient brains is one of the pathological features of Parkinson's disease,the second most common human neurodegenerative disease.Although the detailed pathogenesis accounting for dopaminergic neuron degeneration in Parkinson's disease is still unclear,the advancement of stem cell approaches has shown promise for Parkinson's disease research and therapy.The induced pluripotent stem cells have been commonly used to generate dopaminergic neurons,which has provided valuable insights to improve our understanding of Parkinson's disease pathogenesis and contributed to anti-Parkinson's disease therapies.The current review discusses the practical approaches and potential applications of induced pluripotent stem cell techniques for generating and differentiating dopaminergic neurons from induced pluripotent stem cells.The benefits of induced pluripotent stem cell-based research are highlighted.Various dopaminergic neuron differentiation protocols from induced pluripotent stem cells are compared.The emerging three-dimension-based brain organoid models compared with conventional two-dimensional cell culture are evaluated.Finally,limitations,challenges,and future directions of induced pluripotent stem cell–based approaches are analyzed and proposed,which will be significant to the future application of induced pluripotent stem cell-related techniques for Parkinson's disease.
基金Supported by National Research Foundation of Korea,No.NRF-2021S1A5A8062526.
文摘This article provides a comprehensive analysis of the study by Hou et al,focusing on the complex interplay between psychological and physical factors in the postoperative recovery(POR)of patients with perianal diseases.The study sheds light on how illness perception,anxiety,and depression significantly influence recovery outcomes.Hou et al developed a predictive model that demonstrated high accuracy in identifying patients at risk of poor recovery.The article explores the critical role of pre-operative psychological assessment,highlighting the need for mental health support and personalized recovery plans in enhancing POR quality.A multidisciplinary approach,integrating mental health professionals with surgeons,anesthesiologists,and other specialists,is emphasized to ensure comprehensive care for patients.The study’s findings serve as a call to integrate psychological care into surgical practice to optimize outcomes for patients with perianal diseases.
文摘Objective: To explore the effect of Health Action Process Approach (HAPA) theory in patients with type D personality psoriasis. Methods: A total of 66 patients with type D personality psoriasis admitted to the dermatology department of a top-three hospital in Jingzhou City from November 2022 to July 2023 were selected and divided into control group and test group with 33 cases in each group by random number table method. The control group received routine health education, and the experimental group received health education based on the HAPA theory. Chronic disease self-efficacy scale, hospital anxiety and depression scale and skin disease quality of life scale were used to evaluate the effect of intervention. Results: After 3 months of intervention, the scores of self-efficacy in experimental group were higher than those in control group (P P Conclusion: Health education based on the theory of HAPA can enhance the self-efficacy of patients with type D personality psoriasis, relieve negative emotions and improve their quality of life.
文摘When assessing seismic liquefaction potential with data-driven models,addressing the uncertainties of establishing models,interpreting cone penetration tests(CPT)data and decision threshold is crucial for avoiding biased data selection,ameliorating overconfident models,and being flexible to varying practical objectives,especially when the training and testing data are not identically distributed.A workflow characterized by leveraging Bayesian methodology was proposed to address these issues.Employing a Multi-Layer Perceptron(MLP)as the foundational model,this approach was benchmarked against empirical methods and advanced algorithms for its efficacy in simplicity,accuracy,and resistance to overfitting.The analysis revealed that,while MLP models optimized via maximum a posteriori algorithm suffices for straightforward scenarios,Bayesian neural networks showed great potential for preventing overfitting.Additionally,integrating decision thresholds through various evaluative principles offers insights for challenging decisions.Two case studies demonstrate the framework's capacity for nuanced interpretation of in situ data,employing a model committee for a detailed evaluation of liquefaction potential via Monte Carlo simulations and basic statistics.Overall,the proposed step-by-step workflow for analyzing seismic liquefaction incorporates multifold testing and real-world data validation,showing improved robustness against overfitting and greater versatility in addressing practical challenges.This research contributes to the seismic liquefaction assessment field by providing a structured,adaptable methodology for accurate and reliable analysis.
基金Supported by the National Natural Science Foundation of China under Grant No.52131102.
文摘With the rapid advancement of machine learning technology and its growing adoption in research and engineering applications,an increasing number of studies have embraced data-driven approaches for modeling wind turbine wakes.These models leverage the ability to capture complex,high-dimensional characteristics of wind turbine wakes while offering significantly greater efficiency in the prediction process than physics-driven models.As a result,data-driven wind turbine wake models are regarded as powerful and effective tools for predicting wake behavior and turbine power output.This paper aims to provide a concise yet comprehensive review of existing studies on wind turbine wake modeling that employ data-driven approaches.It begins by defining and classifying machine learning methods to facilitate a clearer understanding of the reviewed literature.Subsequently,the related studies are categorized into four key areas:wind turbine power prediction,data-driven analytic wake models,wake field reconstruction,and the incorporation of explicit physical constraints.The accuracy of data-driven models is influenced by two primary factors:the quality of the training data and the performance of the model itself.Accordingly,both data accuracy and model structure are discussed in detail within the review.
文摘BACKGROUND The root of mesentery dissection is one of the critical maneuvers,especially in borderline resectable pancreatic head cancer.Intra-abdominal chyle leak(CL)including chylous ascites may ensue in up to 10%of patients after pancreatic resections.Globally recognized superior mesenteric artery(SMA)first approaches are invariably performed.The mesenteric dissection through the inferior infracolic approach has been discussed in this study emphasizing its post-operative impact on CL which is the cornerstone of this study.AIM To assess incidence,risk factors,clinical impact of CL following root of mesentery dissection,and the different treatment modalities.METHODS This is a retrospective study incorporating the patients who underwent dissection of the root of mesentery with inferior infracolic SMA first approach pancreat-oduodenectomy for the ventral body and uncinate mass of pancreas in the Department of Gastrointestinal and General Surgery of Kathmandu Medical College and Teaching Hospital from January 1,2021 to February 28,2024.Intraop-erative findings and postoperative outcomes were analyzed.RESULTS In three years,ten patients underwent root of mesentery dissection with inferior infracolic SMA first approach pancreatoduodenectomy.The mean age was 67.6 years with a male-to-female ratio of 4:5.CL was seen in four patients.With virtue of CL,Clavien-Dindo grade Ⅱ or higher morbidity was observed in four patients.Two patients had a hospital stay of more than 20 days with the former having a delayed gastric emptying and the latter with long-term total parenteral nutrition requirement.The mean operative time was 330 minutes.Curative resection was achieved in 100%of the patients.The mean duration of the intensive care unit and hospital stay were 2.55±1.45 days and 15.7±5.32 days,respectively.CONCLUSION Root of mesentery dissection with lymphadenectomy and vascular resection correlated with occurrence of CL.After complete curative resection,these were managed with total parenteral nutrition without adversely impacting outcome.
基金supported by grants from the National Nat-ural Science Foundation of China(82173129)the Innova-tive and Entrepreneurial Talent Doctor of Jiangsu Province,China(JSSCBS20221872)。
文摘Background:Dorsal approach is the potentially effective strategy for minimally invasive liver resection.This study aimed to compare the outcomes between robot-assisted and laparoscopic hemihepatectomy through dorsal approach.Methods:We compared the patients who underwent robot-assisted hemihepatectomy(Rob-HH)and who had laparoscopic hemihepatectomy(Lap-HH)through dorsal approach between January 2020 and December 2022.A 1:1 propensity score-matching(PSM)analysis was performed to minimize bias and confounding factors.Results:Ninety-six patients were included,41 with Rob-HH and 55 with Lap-HH.Among them,58 underwent left hemihepatectomy(LHH)and 38 underwent right hemihepatectomy(RHH).Compared with LapHH group,patients with Rob-HH had less estimated blood loss(median:100.0 vs.300.0 m L,P=0.016),lower blood transfusion rates(4.9%vs.29.1%,P=0.003)and postoperative complication rates(26.8%vs.54.5%,P=0.016).These significant differences consistently existed after PSM and in the LHH subgroups.Furthermore,robot-assisted LHH was associated with decreased Pringle duration(45 vs.60 min,P=0.047).RHH subgroup analysis showed that compared with Lap-RHH,Rob-RHH was associated with less estimated blood loss(200.0 vs.400.0 m L,P=0.013).No significant differences were found in other perioperative outcomes among pre-and post-PSM cohorts,such as Pringle duration,operative time,and hospital stay.Conclusions:The dorsal approach was a safe and feasible strategy for hemi-hepatectomy with favorable outcomes under robot-assisted system in reducing intraoperative blood loss,transfusion,and postoperative complications.
文摘In recent years,the production-oriented approach has been applied in the field of teaching Chinese as a foreign language,providing a new perspective for language and cultural instruction.Currently,several issues exist in cultural teaching,such as the lack of in-depth cultural input,insufficient training in cross-cultural communication skills,and the over-stylization of cultural teaching in the classroom.The production-oriented approach offers a solution to these challenges.This paper seeks to introduce the production-oriented method into the teaching of Chinese culture as a foreign language,using silk culture as a case study for teaching design.The aim is to implement cultural teaching through a new instructional model and to promote the spread of Chinese silk culture.
文摘In this article,the department of the author Joo-Ho Lee“Department of Surgery,Ewha Womans University Mokdong Hospital,Seoul 07985,Republic of Korea”was incorrectly listed.It has been updated as follows:Joo-Ho Lee.Department of Surgery,Nowon Eulji Medical Center,Eulji University,Seoul 01830,Republic of Korea.
基金Supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education,No.NRF-RS-2023-00237287.
文摘The rising prevalence of chronic multimorbidity poses substantial challenges to healthcare systems,necessitating the development of innovative management strategies to optimize patient care and system efficiency.The study by Fontalba-Navas et al investigates the implementation of a novel high complexity unit(HCU)specifically designed to improve the management of patients with chronic complex conditions.By adopting a multidisciplinary approach,the HCU aims to provide comprehensive,patient-centered care that enhances health outcomes and alleviates the strain on traditional hospital services.Utilizing a longitudinal analysis of data from the Basic Minimum Data Set,this study compares hospitalization metrics among the HCU,Internal Medicine,and other departments within a regional hospital throughout 2022.The findings reveal that the HCU's integrated care model significantly reduces readmission rates and boosts patient satisfaction compared to conventional care practices.The study highlights the HCU's potential as a replicable model for managing chronic multimorbidity,emphasizing its effectiveness in minimizing unnecessary hospitalizations and enhancing the overall quality of patient care.This innovative approach not only addresses the complexities associated with chronic multimorbid conditions but also offers a sustainable framework for healthcare systems confronting similar challenges.
基金supported by the National Natural Science Foundation of China(No.22273038 and No.22033004).
文摘Electronic circular dichroism(ECD)spectrum is an important tool for as-sessing molecular chirality.Tradition-al methods,like linear response time-dependent density functional theory(LR-TDDFT),predict ECD spectra well for small or medium-sized molecules,but struggle with large sys-tems due to high computational costs,making it a significant challenge to ac-curately and efficiently predict the ECD properties of complex systems.Within the framework of the generalized energy-based fragmentation(GEBF)method for localized excited states(ESs)calculation,we propose a combination algorithm for calculating rotatory strengths of ESs in condensed phase systems.This algorithm estimates the rotatory strength of the total system by calculating and combin-ing the transition electric and magnetic dipole moments of subsystems.We have used the GEBF method to calculate the ECD properties of chiral drug molecule derivatives,green fluo-rescent protein,and cyclodextrin derivatives,and compared their results with traditional methods or experimental data.The results show that this method can efficiently and accu-rately predict the ECD spectra of these systems.Thus,the GEBF method for ECD spectra demonstrates great potential in the chiral analysis of complex systems and chiral material design,promising to become a powerful theoretical tool in chiral chemistry.
基金supported by the National Youth Top-notch Talent Support Program of China(Grant No.00389335)the National Natural Science Foundation of China(Grant No.52378392)the“Foal Eagle Program”Youth Top-notch Talent Project of Fujian Province(Grant No.00387088).
文摘In situ recycling is one of the most effective methods to dispose of earth pressure balance(EPB)shield waste muck with residual foaming agents with high moisture content.In this context,response surface methodology(RSM)was employed to quantify the effects of independent variables,including flocculant dosage,defoamer dosage,and muck drying mass(MDM)and their interactions on defoaming-flocculation-dewatering indices.The polymeric aluminum chloride(PACL)and hydroxy silicone oil-glycerol polypropylene ether(H-G)were selected as the flocculant and defoamer.The contents of surfactants and foam stabilizers in residual foaming agents were determined using the proposed empirical equation.The defoaming ratio,antifoaming ratio,turbidity,moisture content,filtration loss ratio,and fall cone penetration depth were considered as dependent variables.The accuracy of developed RSM models was verified by the analysis results of variance,residuals,and paired t-test.Combined with the desirability approach,an optimal mixing ratio of 0.078 wt%PACL,0.016 wt%H-G,and 27.882 wt%MDM was recommended,leading to a defoaming ratio of 98.34 vol%for residual foams and a moisture content of 56.72 wt%for pressure-filtration cakes.Our findings were demonstrated to be able to provide useful guidance for prediction and optimization of the in situ recycling indicators of EPB shield waste muck in metro tunnel construction sites.
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funded by the Postgraduate Research and Practice Innovation Program of Jiangsu Province(Grant No.KYCX23_2744)the Fundamental Research Funds for the Central Universities(Grant No.2023XSCX051)the Graduate Innovation Program of China University of Mining and Technology(Grant No.2023WLKXJ182).
文摘Microwave-assisted rock-breaking technology,as a novel hybrid approach,is anticipated to facilitate the efficient excavation of complex rock formations.It is therefore crucial to understand the damage and failure mechanisms of rocks that have been subjected to irradiation.In this study,uniaxial compression experiments were conducted on granite specimens after 1.4 kW microwave irradiation for varying durations.Furthermore,a numerical method was proposed to solve electromagnetic-thermal-mechanical coupling problems by integrating finite and discrete elements.The results demonstrated a differential temperature distribution(high temperature in the middle and low-temperature areas at the ends)in the granite specimens under microwave irradiation,which resulted in a notable reduction in their physical and mechanical properties.As the duration of irradiation increased,the rate of heating and the extent of strength reduction both diminished,while the morphology and distribution of cracks at ultimate failure became increasingly complex.The numerical method effectively addresses the simulation challenges associated with the electromagnetic selective heating of granite containing multiple polar minerals under microwave irradiation.This approach accounted for the non-uniform thermal expansion of the minerals and provided a comprehensive model of damage progression under compression.
基金supported by the National Natural Science Foundation of China (No.62173281,52377217,U23A20651)Sichuan Science and Technology Program (No.24NSFSC0024,23ZDYF0734,23NSFSC1436)+2 种基金Dazhou City School Cooperation Project (No.DZXQHZ006)Technopole Talent Summit Project (No.KJCRCFH08)Robert Gordon University。
文摘Lithium-ion batteries are the preferred green energy storage method and are equipped with intelligent battery management systems(BMSs)that efficiently manage the batteries.This not only ensures the safety performance of the batteries but also significantly improves their efficiency and reduces their damage rate.Throughout their whole life cycle,lithium-ion batteries undergo aging and performance degradation due to diverse external environments and irregular degradation of internal materials.This degradation is reflected in the state of health(SOH)assessment.Therefore,this review offers the first comprehensive analysis of battery SOH estimation strategies across the entire lifecycle over the past five years,highlighting common research focuses rooted in data-driven methods.It delves into various dimensions such as dataset integration and preprocessing,health feature parameter extraction,and the construction of SOH estimation models.These approaches unearth hidden insights within data,addressing the inherent tension between computational complexity and estimation accuracy.To enha nce support for in-vehicle implementation,cloud computing,and the echelon technologies of battery recycling,remanufacturing,and reuse,as well as to offer insights into these technologies,a segmented management approach will be introduced in the future.This will encompass source domain data processing,multi-feature factor reconfiguration,hybrid drive modeling,parameter correction mechanisms,and fulltime health management.Based on the best SOH estimation outcomes,health strategies tailored to different stages can be devised in the future,leading to the establishment of a comprehensive SOH assessment framework.This will mitigate cross-domain distribution disparities and facilitate adaptation to a broader array of dynamic operation protocols.This article reviews the current research landscape from four perspectives and discusses the challenges that lie ahead.Researchers and practitioners can gain a comprehensive understanding of battery SOH estimation methods,offering valuable insights for the development of advanced battery management systems and embedded application research.
