This paper aims to conduct a systematic literature review(SLR)using an artificial intelligence(AI)approach to predict and diagnose diabetes mellitus.After reviewing the literature published from 2015–2025,the paper a...This paper aims to conduct a systematic literature review(SLR)using an artificial intelligence(AI)approach to predict and diagnose diabetes mellitus.After reviewing the literature published from 2015–2025,the paper aims to identify the most effective AI techniques,the most used datasets,the most widely used data preprocessing techniques,and the most common issues.After analyzing the literature,it has been found that convolutional neural networks(CNNs)and long short-term memory(LSTM)networks are deep learning models that have shown high accuracy in diabetes prediction.Recursive feature elimination(RFE)and SMOTE are feature selection techniques that have significantly improved model accuracy,training time,and interpretability.Amidst this technological advancement,some existing issues persist:data imbalance,the inapplicability of techniques,computational limitations,and a lack of real-time application in a healthcare environment.The literature review has also identified the need for robust,interpretable,and scalable AI systems capable of handling large volumes of data,including real-world data,in the healthcare industry.Furthermore,it has been identified that the benefits should be integrated with wearable health monitoring systems and the development of privacy-preserving models to ensure continuous,secure,and proactive diabetes management.展开更多
Understanding spatial heterogeneity in groundwater responses to multiple factors is critical for water resource management in coastal cities.Daily groundwater depth(GWD)data from 43 wells(2018-2022)were collected in t...Understanding spatial heterogeneity in groundwater responses to multiple factors is critical for water resource management in coastal cities.Daily groundwater depth(GWD)data from 43 wells(2018-2022)were collected in three coastal cities in Jiangsu Province,China.Seasonal and Trend decomposition using Loess(STL)together with wavelet analysis and empirical mode decomposition were applied to identify tide-influenced wells while remaining wells were grouped by hierarchical clustering analysis(HCA).Machine learning models were developed to predict GWD,then their response to natural conditions and human activities was assessed by the Shapley Additive exPlanations(SHAP)method.Results showed that eXtreme Gradient Boosting(XGB)was superior to other models in terms of prediction performance and computational efficiency(R^(2)>0.95).GWD in Yancheng and southern Lianyungang were greater than those in Nantong,exhibiting larger fluctuations.Groundwater within 5 km of the coastline was affected by tides,with more pronounced effects in agricultural areas compared to urban areas.Shallow groundwater(3-7 m depth)responded immediately(0-1 day)to rainfall,primarily influenced by farmland and topography(slope and distance from rivers).Rainfall recharge to groundwater peaked at 50%farmland coverage,but this effect was suppressed by high temperatures(>30℃)which intensified as distance from rivers increased,especially in forest and grassland.Deep groundwater(>10 m)showed delayed responses to rainfall(1-4 days)and temperature(10-15 days),with GDP as the primary influence,followed by agricultural irrigation and population density.Farmland helped to maintain stable GWD in low population density regions,while excessive farmland coverage(>90%)led to overexploitation.In the early stages of GDP development,increased industrial and agricultural water demand led to GWD decline,but as GDP levels significantly improved,groundwater consumption pressure gradually eased.This methodological framework is applicable not only to coastal cities in China but also could be extended to coastal regions worldwide.展开更多
Floods and storm surges pose significant threats to coastal regions worldwide,demanding timely and accurate early warning systems(EWS)for disaster preparedness.Traditional numerical and statistical methods often fall ...Floods and storm surges pose significant threats to coastal regions worldwide,demanding timely and accurate early warning systems(EWS)for disaster preparedness.Traditional numerical and statistical methods often fall short in capturing complex,nonlinear,and real-time environmental dynamics.In recent years,machine learning(ML)and deep learning(DL)techniques have emerged as promising alternatives for enhancing the accuracy,speed,and scalability of EWS.This review critically evaluates the evolution of ML models—such as Artificial Neural Networks(ANN),Convolutional Neural Networks(CNN),and Long Short-Term Memory(LSTM)—in coastal flood prediction,highlighting their architectures,data requirements,performance metrics,and implementation challenges.A unique contribution of this work is the synthesis of real-time deployment challenges including latency,edge-cloud tradeoffs,and policy-level integration,areas often overlooked in prior literature.Furthermore,the review presents a comparative framework of model performance across different geographic and hydrologic settings,offering actionable insights for researchers and practitioners.Limitations of current AI-driven models,such as interpretability,data scarcity,and generalization across regions,are discussed in detail.Finally,the paper outlines future research directions including hybrid modelling,transfer learning,explainable AI,and policy-aware alert systems.By bridging technical performance and operational feasibility,this review aims to guide the development of next-generation intelligent EWS for resilient and adaptive coastal management.展开更多
Sporadic E(Es)layers in the ionosphere are characterized by intense plasma irregularities in the E region at altitudes of 90-130 km.Because they can significantly influence radio communications and navigation systems,...Sporadic E(Es)layers in the ionosphere are characterized by intense plasma irregularities in the E region at altitudes of 90-130 km.Because they can significantly influence radio communications and navigation systems,accurate forecasting of Es layers is crucial for ensuring the precision and dependability of navigation satellite systems.In this study,we present Es predictions made by an empirical model and by a deep learning model,and analyze their differences comprehensively by comparing the model predictions to satellite RO measurements and ground-based ionosonde observations.The deep learning model exhibited significantly better performance,as indicated by its high coefficient of correlation(r=0.87)with RO observations and predictions,than did the empirical model(r=0.53).This study highlights the importance of integrating artificial intelligence technology into ionosphere modelling generally,and into predicting Es layer occurrences and characteristics,in particular.展开更多
To perform landslide susceptibility prediction(LSP),it is important to select appropriate mapping unit and landslide-related conditioning factors.The efficient and automatic multi-scale segmentation(MSS)method propose...To perform landslide susceptibility prediction(LSP),it is important to select appropriate mapping unit and landslide-related conditioning factors.The efficient and automatic multi-scale segmentation(MSS)method proposed by the authors promotes the application of slope units.However,LSP modeling based on these slope units has not been performed.Moreover,the heterogeneity of conditioning factors in slope units is neglected,leading to incomplete input variables of LSP modeling.In this study,the slope units extracted by the MSS method are used to construct LSP modeling,and the heterogeneity of conditioning factors is represented by the internal variations of conditioning factors within slope unit using the descriptive statistics features of mean,standard deviation and range.Thus,slope units-based machine learning models considering internal variations of conditioning factors(variant slope-machine learning)are proposed.The Chongyi County is selected as the case study and is divided into 53,055 slope units.Fifteen original slope unit-based conditioning factors are expanded to 38 slope unit-based conditioning factors through considering their internal variations.Random forest(RF)and multi-layer perceptron(MLP)machine learning models are used to construct variant Slope-RF and Slope-MLP models.Meanwhile,the Slope-RF and Slope-MLP models without considering the internal variations of conditioning factors,and conventional grid units-based machine learning(Grid-RF and MLP)models are built for comparisons through the LSP performance assessments.Results show that the variant Slopemachine learning models have higher LSP performances than Slope-machine learning models;LSP results of variant Slope-machine learning models have stronger directivity and practical application than Grid-machine learning models.It is concluded that slope units extracted by MSS method can be appropriate for LSP modeling,and the heterogeneity of conditioning factors within slope units can more comprehensively reflect the relationships between conditioning factors and landslides.The research results have important reference significance for land use and landslide prevention.展开更多
The Indian Himalayan region is frequently experiencing climate change-induced landslides.Thus,landslide susceptibility assessment assumes greater significance for lessening the impact of a landslide hazard.This paper ...The Indian Himalayan region is frequently experiencing climate change-induced landslides.Thus,landslide susceptibility assessment assumes greater significance for lessening the impact of a landslide hazard.This paper makes an attempt to assess landslide susceptibility in Shimla district of the northwest Indian Himalayan region.It examined the effectiveness of random forest(RF),multilayer perceptron(MLP),sequential minimal optimization regression(SMOreg)and bagging ensemble(B-RF,BSMOreg,B-MLP)models.A landslide inventory map comprising 1052 locations of past landslide occurrences was classified into training(70%)and testing(30%)datasets.The site-specific influencing factors were selected by employing a multicollinearity test.The relationship between past landslide occurrences and influencing factors was established using the frequency ratio method.The effectiveness of machine learning models was verified through performance assessors.The landslide susceptibility maps were validated by the area under the receiver operating characteristic curves(ROC-AUC),accuracy,precision,recall and F1-score.The key performance metrics and map validation demonstrated that the BRF model(correlation coefficient:0.988,mean absolute error:0.010,root mean square error:0.058,relative absolute error:2.964,ROC-AUC:0.947,accuracy:0.778,precision:0.819,recall:0.917 and F-1 score:0.865)outperformed the single classifiers and other bagging ensemble models for landslide susceptibility.The results show that the largest area was found under the very high susceptibility zone(33.87%),followed by the low(27.30%),high(20.68%)and moderate(18.16%)susceptibility zones.The factors,namely average annual rainfall,slope,lithology,soil texture and earthquake magnitude have been identified as the influencing factors for very high landslide susceptibility.Soil texture,lineament density and elevation have been attributed to high and moderate susceptibility.Thus,the study calls for devising suitable landslide mitigation measures in the study area.Structural measures,an immediate response system,community participation and coordination among stakeholders may help lessen the detrimental impact of landslides.The findings from this study could aid decision-makers in mitigating future catastrophes and devising suitable strategies in other geographical regions with similar geological characteristics.展开更多
In recent years evidence has emerged suggesting that Mini-basketball training program(MBTP)can be an effec-tive intervention method to improve social communication(SC)impairments and restricted and repetitive beha-vio...In recent years evidence has emerged suggesting that Mini-basketball training program(MBTP)can be an effec-tive intervention method to improve social communication(SC)impairments and restricted and repetitive beha-viors(RRBs)in preschool children suffering from autism spectrum disorder(ASD).However,there is a considerable degree if interindividual variability concerning these social outcomes and thus not all preschool chil-dren with ASD profit from a MBTP intervention to the same extent.In order to make more accurate predictions which preschool children with ASD can benefit from an MBTP intervention or which preschool children with ASD need additional interventions to achieve behavioral improvements,further research is required.This study aimed to investigate which individual factors of preschool children with ASD can predict MBTP intervention out-comes concerning SC impairments and RRBs.Then,test the performance of machine learning models in predict-ing intervention outcomes based on these factors.Participants were 26 preschool children with ASD who enrolled in a quasi-experiment and received MBTP intervention.Baseline demographic variables(e.g.,age,body,mass index[BMI]),indicators of physicalfitness(e.g.,handgrip strength,balance performance),performance in execu-tive function,severity of ASD symptoms,level of SC impairments,and severity of RRBs were obtained to predict treatment outcomes after MBTP intervention.Machine learning models were established based on support vector machine algorithm were implemented.For comparison,we also employed multiple linear regression models in statistics.Ourfindings suggest that in preschool children with ASD symptomatic severity(r=0.712,p<0.001)and baseline SC impairments(r=0.713,p<0.001)are predictors for intervention outcomes of SC impair-ments.Furthermore,BMI(r=-0.430,p=0.028),symptomatic severity(r=0.656,p<0.001),baseline SC impair-ments(r=0.504,p=0.009)and baseline RRBs(r=0.647,p<0.001)can predict intervention outcomes of RRBs.Statistical models predicted 59.6%of variance in post-treatment SC impairments(MSE=0.455,RMSE=0.675,R2=0.596)and 58.9%of variance in post-treatment RRBs(MSE=0.464,RMSE=0.681,R2=0.589).Machine learning models predicted 83%of variance in post-treatment SC impairments(MSE=0.188,RMSE=0.434,R2=0.83)and 85.9%of variance in post-treatment RRBs(MSE=0.051,RMSE=0.226,R2=0.859),which were better than statistical models.Ourfindings suggest that baseline characteristics such as symptomatic severity of 144 IJMHP,2022,vol.24,no.2 ASD symptoms and SC impairments are important predictors determining MBTP intervention-induced improvements concerning SC impairments and RBBs.Furthermore,the current study revealed that machine learning models can successfully be applied to predict the MBTP intervention-related outcomes in preschool chil-dren with ASD,and performed better than statistical models.Ourfindings can help to inform which preschool children with ASD are most likely to benefit from an MBTP intervention,and they might provide a reference for the development of personalized intervention programs for preschool children with ASD.展开更多
BACKGROUND Liver transplantation(LT)is a life-saving intervention for patients with end-stage liver disease.However,the equitable allocation of scarce donor organs remains a formidable challenge.Prognostic tools are p...BACKGROUND Liver transplantation(LT)is a life-saving intervention for patients with end-stage liver disease.However,the equitable allocation of scarce donor organs remains a formidable challenge.Prognostic tools are pivotal in identifying the most suitable transplant candidates.Traditionally,scoring systems like the model for end-stage liver disease have been instrumental in this process.Nevertheless,the landscape of prognostication is undergoing a transformation with the integration of machine learning(ML)and artificial intelligence models.AIM To assess the utility of ML models in prognostication for LT,comparing their performance and reliability to established traditional scoring systems.METHODS Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines,we conducted a thorough and standardized literature search using the PubMed/MEDLINE database.Our search imposed no restrictions on publication year,age,or gender.Exclusion criteria encompassed non-English studies,review articles,case reports,conference papers,studies with missing data,or those exhibiting evident methodological flaws.RESULTS Our search yielded a total of 64 articles,with 23 meeting the inclusion criteria.Among the selected studies,60.8%originated from the United States and China combined.Only one pediatric study met the criteria.Notably,91%of the studies were published within the past five years.ML models consistently demonstrated satisfactory to excellent area under the receiver operating characteristic curve values(ranging from 0.6 to 1)across all studies,surpassing the performance of traditional scoring systems.Random forest exhibited superior predictive capabilities for 90-d mortality following LT,sepsis,and acute kidney injury(AKI).In contrast,gradient boosting excelled in predicting the risk of graft-versus-host disease,pneumonia,and AKI.CONCLUSION This study underscores the potential of ML models in guiding decisions related to allograft allocation and LT,marking a significant evolution in the field of prognostication.展开更多
This study employs nine distinct deep learning models to categorize 12,444 blood cell images and automatically extract from them relevant information with an accuracy that is beyond that achievable with traditional te...This study employs nine distinct deep learning models to categorize 12,444 blood cell images and automatically extract from them relevant information with an accuracy that is beyond that achievable with traditional techniques.The work is intended to improve current methods for the assessment of human health through measurement of the distribution of four types of blood cells,namely,eosinophils,neutrophils,monocytes,and lymphocytes,known for their relationship with human body damage,inflammatory regions,and organ illnesses,in particular,and with the health of the immune system and other hazards,such as cardiovascular disease or infections,more in general.The results of the experiments show that the deep learning models can automatically extract features from the blood cell images and properly classify them with an accuracy of 98%,97%,and 89%,respectively,with regard to the training,verification,and testing of the corresponding datasets.展开更多
Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced b...Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced by other important financial indexes across the world such as commodity price and financial technical indicators. This paper systematically investigated four supervised learning models, including Logistic Regression, Gaussian Discriminant Analysis (GDA), Naive Bayes and Support Vector Machine (SVM) in the forecast of S&P 500 index. After several experiments of optimization in features and models, especially the SVM kernel selection and feature selection for different models, this paper concludes that a SVM model with a Radial Basis Function (RBF) kernel can achieve an accuracy rate of 62.51% for the future market trend of the S&P 500 index.展开更多
Production performance prediction of tight gas reservoirs is crucial to the estimation of ultimate recovery,which has an important impact on gas field development planning and economic evaluation.Owing to the model’s...Production performance prediction of tight gas reservoirs is crucial to the estimation of ultimate recovery,which has an important impact on gas field development planning and economic evaluation.Owing to the model’s simplicity,the decline curve analysis method has been widely used to predict production performance.The advancement of deep-learning methods provides an intelligent way of analyzing production performance in tight gas reservoirs.In this paper,a sequence learning method to improve the accuracy and efficiency of tight gas production forecasting is proposed.The sequence learning methods used in production performance analysis herein include the recurrent neural network(RNN),long short-term memory(LSTM)neural network,and gated recurrent unit(GRU)neural network,and their performance in the tight gas reservoir production prediction is investigated and compared.To further improve the performance of the sequence learning method,the hyperparameters in the sequence learning methods are optimized through a particle swarm optimization algorithm,which can greatly simplify the optimization process of the neural network model in an automated manner.Results show that the optimized GRU and RNN models have more compact neural network structures than the LSTM model and that the GRU is more efficiently trained.The predictive performance of LSTM and GRU is similar,and both are better than the RNN and the decline curve analysis model and thus can be used to predict tight gas production.展开更多
Machine learning models were used to improve the accuracy of China Meteorological Administration Multisource Precipitation Analysis System(CMPAS)in complex terrain areas by combining rain gauge precipitation with topo...Machine learning models were used to improve the accuracy of China Meteorological Administration Multisource Precipitation Analysis System(CMPAS)in complex terrain areas by combining rain gauge precipitation with topographic factors like altitude,slope,slope direction,slope variability,surface roughness,and meteorological factors like temperature and wind speed.The results of the correction demonstrated that the ensemble learning method has a considerably corrective effect and the three methods(Random Forest,AdaBoost,and Bagging)adopted in the study had similar results.The mean bias between CMPAS and 85%of automatic weather stations has dropped by more than 30%.The plateau region displays the largest accuracy increase,the winter season shows the greatest error reduction,and decreasing precipitation improves the correction outcome.Additionally,the heavy precipitation process’precision has improved to some degree.For individual stations,the revised CMPAS error fluctuation range is significantly reduced.展开更多
Unconventional reservoirs have become the main alternative for increasing oil and gas reserves around the world. Owing to their ultralow permeability properties and special pore structure, hydraulic fracturing technol...Unconventional reservoirs have become the main alternative for increasing oil and gas reserves around the world. Owing to their ultralow permeability properties and special pore structure, hydraulic fracturing technology is necessary to realize the efficient development and economic management of unconventional resources. To maximize the production capacity of wells, several fracture parameters, including fracture number, length, width, conductivity, and spacing, need to be optimized effectively. The optimization of hydraulic fracture parameters in shale gas reservoirs generally demands intensive computations owing to the necessity of numerous physicalmodel simulations. This study proposes a machine learning (ML)–assisted global optimization framework to rapidly obtain optimal fracture parameters. We employed three supervised ML models, including the radialbasis function, K-nearest neighbor, and multilayer perceptron, to emulate the relationship between fracture parameters and shale gas productivity for multistage fractured horizontal wells. Firstly, several forward shale gas simulations with embedded discrete fracture models generate training samples. Then, the samples are divided into training and testing samples to train these ML models and optimize network hyper parameters, respectively. Finally, the trained ML models are combined with an intelligent differential evolution algorithm to optimize the fracture parameters. This novel method has been applied to a naturally fractured reservoir model based on the real-field Barnett shale formation. The obtained results are compared with those of conventional optimizations with high-fidelity models. The results confirm the superiority of the proposed method owing to its very low computational cost. The use of ML modeling technology and an intelligent optimization algorithm could greatly contribute to simulation optimization and design, prompting progress in the intelligent development of unconventional oil and gas reservoirs in China.展开更多
Background Cotton is one of the most important commercial crops after food crops,especially in countries like India,where it’s grown extensively under rainfed conditions.Because of its usage in multiple industries,su...Background Cotton is one of the most important commercial crops after food crops,especially in countries like India,where it’s grown extensively under rainfed conditions.Because of its usage in multiple industries,such as textile,medicine,and automobile industries,it has greater commercial importance.The crop’s performance is greatly influenced by prevailing weather dynamics.As climate changes,assessing how weather changes affect crop performance is essential.Among various techniques that are available,crop models are the most effective and widely used tools for predicting yields.Results This study compares statistical and machine learning models to assess their ability to predict cotton yield across major producing districts of Karnataka,India,utilizing a long-term dataset spanning from 1990 to 2023 that includes yield and weather factors.The artificial neural networks(ANNs)performed superiorly with acceptable yield deviations ranging within±10%during both vegetative stage(F1)and mid stage(F2)for cotton.The model evaluation metrics such as root mean square error(RMSE),normalized root mean square error(nRMSE),and modelling efficiency(EF)were also within the acceptance limits in most districts.Furthermore,the tested ANN model was used to assess the importance of the dominant weather factors influencing crop yield in each district.Specifically,the use of morning relative humidity as an individual parameter and its interaction with maximum and minimum tempera-ture had a major influence on cotton yield in most of the yield predicted districts.These differences highlighted the differential interactions of weather factors in each district for cotton yield formation,highlighting individual response of each weather factor under different soils and management conditions over the major cotton growing districts of Karnataka.Conclusions Compared with statistical models,machine learning models such as ANNs proved higher efficiency in forecasting the cotton yield due to their ability to consider the interactive effects of weather factors on yield forma-tion at different growth stages.This highlights the best suitability of ANNs for yield forecasting in rainfed conditions and for the study on relative impacts of weather factors on yield.Thus,the study aims to provide valuable insights to support stakeholders in planning effective crop management strategies and formulating relevant policies.展开更多
Introduction:Clinical manifestations are essential for early diagnosis of influenza-like illness(ILI).Machine learning models for influenza prediction were developed and a new ILI definition was introduced.Methods:A r...Introduction:Clinical manifestations are essential for early diagnosis of influenza-like illness(ILI).Machine learning models for influenza prediction were developed and a new ILI definition was introduced.Methods:A retrospective cohort study was conducted at three hospitals in southwest China during June 2022 and May 2023.Artificial intelligence was used to extract variables from medical records and XGBOOST algorithm was used to develop prediction models for the total population and three age subgroups.A new ILI definition was introduced based on the optimal model and its performance was compared with WHO,China CDC,and USA CDC definitions.Results:Totally 200,135 patients were included.4,249(36.2%)were confirmed influenza.The predictors of the optimal model included epidemiological characteristics,important symptoms and signs,and age for the total population[Area under curve(AUC)0.734(0.710–0.750),accuracy 0.689(0.669–0.772)].The new ILI definition was fever(≥37.9℃)with cough or rhinorrhea,and its AUC,sensitivity,and specificity for diagnosing influenza were 0.618(0.598–0.639),0.665 and 0.572,outperformed the WHO,China CDC,and USA CDC definitions(P<0.05).Conclusions:Fever,cough,and rhinorrhea maybe the most important indicators for influenza surveillance.展开更多
This research explored a novel multimodal approach for disease management in cauliflower crops.With the rising challenges in sustainable agriculture,the research focused on a patch spraying method to control disease a...This research explored a novel multimodal approach for disease management in cauliflower crops.With the rising challenges in sustainable agriculture,the research focused on a patch spraying method to control disease and reduce crop losses and environmental impact.For non-destructive disease assessment,a spectral sensor was used to collect spectral information from diseased and healthy cauliflower parts.The spectral data sets were analyzed using decision tree and support vector machine(SVM)algorithms to identify the most accurate model for distinguishing diseased and healthy plants.The chosen model was integrated with a low-volume sprayer(50-150 L·ha^(-1)),equipped with an electronic control unit for targeted spraying based on sensor-detected regions.The decision tree model achieved 89.9% testing accuracy,while the SVM model achieved 96.7% accuracy using hyperparameters:cost of 10.0 and tolerance of 0.001.The research successfully demonstrated the integration of spectral sensors,machine learning,and targeted spraying technology for precise input application.Additionally,the optimized sprayer achieved a 72.5% reduction in chemical usage and a significant time-saving of 21.0% compared to a standard sprayer for black rot-infested crops.These findings highlight the potential efficiency and resource conservation benefits of innovative sprayer technology in precision agriculture and disease management.展开更多
Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server.Despite rapid progress,federated learning still faces s...Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server.Despite rapid progress,federated learning still faces several unsolved challenges.Specifically,communication costs and system heterogeneity,such as nonidentical data distribution,hinder federated learning's progress.Several approaches have recently emerged for federated learning involving heterogeneous clients with varying computational capabilities(namely,heterogeneous federated learning).However,heterogeneous federated learning faces two key challenges:optimising model size and determining client selection ratios.Moreover,efficiently aggregating local models from clients with diverse capabilities is crucial for addressing system heterogeneity and communication efficiency.This paper proposes an evolutionary multiobjective optimisation framework for heterogeneous federated learning(MOHFL)to address these issues.Our approach elegantly formulates and solves a biobjective optimisation problem that minimises communication cost and model error rate.The decision variables in this framework comprise model sizes and client selection ratios for each Q client cluster,yielding a total of 2×Q optimisation parameters to be tuned.We develop a partition-based strategy for MOHFL that segregates clients into clusters based on their communication and computation capabilities.Additionally,we implement an adaptive model sizing mechanism that dynamically assigns appropriate subnetwork architectures to clients based on their computational constraints.We also propose a unified aggregation framework to combine models of varying sizes from heterogeneous clients effectively.Extensive experiments on multiple datasets demonstrate the effectiveness and superiority of our proposed method compared to existing approaches.展开更多
The prediction of the Tropical Cyclone(TC)intensity helps the government to take proper precautions and disseminate appropriate warnings to civilians.Intensity prediction for TC is a very challenging task due to its d...The prediction of the Tropical Cyclone(TC)intensity helps the government to take proper precautions and disseminate appropriate warnings to civilians.Intensity prediction for TC is a very challenging task due to its dynamically changing internal and external impact factors.We proposed a system to predict TC intensity using CNN-based ensemble deep-learning models that are trained by both satellite images and numerical data of the TC.This paper presents a thorough examination of several deep-learning models such as CNN,Recurrent Neural Networks(RNN)and transfer learning models(AlexNet and VGG)to determine their effectiveness in forecasting TC intensity.Our focus is on four widely recognized models:AlexNet,VGG16,RNN and,a customized CNN-based ensemble model all of which were trained exclusively on image data,as well as an ensemble model that utilized both image and numerical datasets for training.Our analysis evaluates the performance of each model in terms of the loss incurred.The results provide a comparative assessment of the deep learning models selected and offer insights into their respective prediction loss in the form of Mean Square Error(MSE)as 194 in 100 epochs and execution time 1229 s to forecasting TC intensity.We also emphasize the potential benefits of incorporating both image and numerical data into an ensemble model,which can lead to improved prediction accuracy.This research provides valuable knowledge to the field of meteorology and disaster management,paving the way for more resilient and precise TC intensity forecasting models.展开更多
Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions.In this work,we develop a new and general approach of assessing model domain and de...Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions.In this work,we develop a new and general approach of assessing model domain and demonstrate that our approach provides accurate and meaningful domain designation across multiple model types and material property data sets.Our approach assesses the distance between data in feature space using kernel density estimation,where this distance provides an effective tool for domain determination.We show that chemical groups considered unrelated based on chemical knowledge exhibit significant dissimilarities by our measure.We also show that high measures of dissimilarity are associated with poor model performance(i.e.,high residual magnitudes)and poor estimates of model uncertainty(i.e.,unreliable uncertainty estimation).Automated tools are provided to enable researchers to establish acceptable dissimilarity thresholds to identify whether new predictions of their own machine learning models are in-domain versus out-of-domain.展开更多
The integration of machine learning(ML)models enhances the efficiency,affordability,and reliability of feature detection in microscopy,yet their development and applicability are hindered by the dependency on scarce a...The integration of machine learning(ML)models enhances the efficiency,affordability,and reliability of feature detection in microscopy,yet their development and applicability are hindered by the dependency on scarce and often flawed manually labeled datasets with a lack of domain awareness.We addressed these challenges by creating a physics-based synthetic image and data generator,resulting in an ML model that achieves comparable precision(0.86),recall(0.63),F1 scores(0.71),and engineering property predictions(R2=0.82)to amodel trained on human-labeled data.We enhanced both models by using feature prediction confidence scores to derive an image-wide confidence metric,enabling simple thresholding to eliminate ambiguous and out-of-domain images,resulting in performance boosts of 5–30%with a filtering-out rate of 25%.Our study demonstrates that synthetic data can eliminate human reliance in ML and provides a means for domain awareness in cases where many feature detections per image are needed.展开更多
文摘This paper aims to conduct a systematic literature review(SLR)using an artificial intelligence(AI)approach to predict and diagnose diabetes mellitus.After reviewing the literature published from 2015–2025,the paper aims to identify the most effective AI techniques,the most used datasets,the most widely used data preprocessing techniques,and the most common issues.After analyzing the literature,it has been found that convolutional neural networks(CNNs)and long short-term memory(LSTM)networks are deep learning models that have shown high accuracy in diabetes prediction.Recursive feature elimination(RFE)and SMOTE are feature selection techniques that have significantly improved model accuracy,training time,and interpretability.Amidst this technological advancement,some existing issues persist:data imbalance,the inapplicability of techniques,computational limitations,and a lack of real-time application in a healthcare environment.The literature review has also identified the need for robust,interpretable,and scalable AI systems capable of handling large volumes of data,including real-world data,in the healthcare industry.Furthermore,it has been identified that the benefits should be integrated with wearable health monitoring systems and the development of privacy-preserving models to ensure continuous,secure,and proactive diabetes management.
基金supported by the Natural Science Foundation of Jiangsu province,China(BK20240937)the Belt and Road Special Foundation of the National Key Laboratory of Water Disaster Prevention(2022491411,2021491811)the Basal Research Fund of Central Public Welfare Scientific Institution of Nanjing Hydraulic Research Institute(Y223006).
文摘Understanding spatial heterogeneity in groundwater responses to multiple factors is critical for water resource management in coastal cities.Daily groundwater depth(GWD)data from 43 wells(2018-2022)were collected in three coastal cities in Jiangsu Province,China.Seasonal and Trend decomposition using Loess(STL)together with wavelet analysis and empirical mode decomposition were applied to identify tide-influenced wells while remaining wells were grouped by hierarchical clustering analysis(HCA).Machine learning models were developed to predict GWD,then their response to natural conditions and human activities was assessed by the Shapley Additive exPlanations(SHAP)method.Results showed that eXtreme Gradient Boosting(XGB)was superior to other models in terms of prediction performance and computational efficiency(R^(2)>0.95).GWD in Yancheng and southern Lianyungang were greater than those in Nantong,exhibiting larger fluctuations.Groundwater within 5 km of the coastline was affected by tides,with more pronounced effects in agricultural areas compared to urban areas.Shallow groundwater(3-7 m depth)responded immediately(0-1 day)to rainfall,primarily influenced by farmland and topography(slope and distance from rivers).Rainfall recharge to groundwater peaked at 50%farmland coverage,but this effect was suppressed by high temperatures(>30℃)which intensified as distance from rivers increased,especially in forest and grassland.Deep groundwater(>10 m)showed delayed responses to rainfall(1-4 days)and temperature(10-15 days),with GDP as the primary influence,followed by agricultural irrigation and population density.Farmland helped to maintain stable GWD in low population density regions,while excessive farmland coverage(>90%)led to overexploitation.In the early stages of GDP development,increased industrial and agricultural water demand led to GWD decline,but as GDP levels significantly improved,groundwater consumption pressure gradually eased.This methodological framework is applicable not only to coastal cities in China but also could be extended to coastal regions worldwide.
文摘Floods and storm surges pose significant threats to coastal regions worldwide,demanding timely and accurate early warning systems(EWS)for disaster preparedness.Traditional numerical and statistical methods often fall short in capturing complex,nonlinear,and real-time environmental dynamics.In recent years,machine learning(ML)and deep learning(DL)techniques have emerged as promising alternatives for enhancing the accuracy,speed,and scalability of EWS.This review critically evaluates the evolution of ML models—such as Artificial Neural Networks(ANN),Convolutional Neural Networks(CNN),and Long Short-Term Memory(LSTM)—in coastal flood prediction,highlighting their architectures,data requirements,performance metrics,and implementation challenges.A unique contribution of this work is the synthesis of real-time deployment challenges including latency,edge-cloud tradeoffs,and policy-level integration,areas often overlooked in prior literature.Furthermore,the review presents a comparative framework of model performance across different geographic and hydrologic settings,offering actionable insights for researchers and practitioners.Limitations of current AI-driven models,such as interpretability,data scarcity,and generalization across regions,are discussed in detail.Finally,the paper outlines future research directions including hybrid modelling,transfer learning,explainable AI,and policy-aware alert systems.By bridging technical performance and operational feasibility,this review aims to guide the development of next-generation intelligent EWS for resilient and adaptive coastal management.
基金supported by the Project of Stable Support for Youth Team in Basic Research Field,CAS(grant No.YSBR-018)the National Natural Science Foundation of China(grant Nos.42188101,42130204)+4 种基金the B-type Strategic Priority Program of CAS(grant no.XDB41000000)the National Natural Science Foundation of China(NSFC)Distinguished Overseas Young Talents Program,Innovation Program for Quantum Science and Technology(2021ZD0300301)the Open Research Project of Large Research Infrastructures of CAS-“Study on the interaction between low/mid-latitude atmosphere and ionosphere based on the Chinese Meridian Project”.The project was supported also by the National Key Laboratory of Deep Space Exploration(Grant No.NKLDSE2023A002)the Open Fund of Anhui Provincial Key Laboratory of Intelligent Underground Detection(Grant No.APKLIUD23KF01)the China National Space Administration(CNSA)pre-research Project on Civil Aerospace Technologies No.D010305,D010301.
文摘Sporadic E(Es)layers in the ionosphere are characterized by intense plasma irregularities in the E region at altitudes of 90-130 km.Because they can significantly influence radio communications and navigation systems,accurate forecasting of Es layers is crucial for ensuring the precision and dependability of navigation satellite systems.In this study,we present Es predictions made by an empirical model and by a deep learning model,and analyze their differences comprehensively by comparing the model predictions to satellite RO measurements and ground-based ionosonde observations.The deep learning model exhibited significantly better performance,as indicated by its high coefficient of correlation(r=0.87)with RO observations and predictions,than did the empirical model(r=0.53).This study highlights the importance of integrating artificial intelligence technology into ionosphere modelling generally,and into predicting Es layer occurrences and characteristics,in particular.
基金funded by the Natural Science Foundation of China(Grant Nos.41807285,41972280 and 52179103).
文摘To perform landslide susceptibility prediction(LSP),it is important to select appropriate mapping unit and landslide-related conditioning factors.The efficient and automatic multi-scale segmentation(MSS)method proposed by the authors promotes the application of slope units.However,LSP modeling based on these slope units has not been performed.Moreover,the heterogeneity of conditioning factors in slope units is neglected,leading to incomplete input variables of LSP modeling.In this study,the slope units extracted by the MSS method are used to construct LSP modeling,and the heterogeneity of conditioning factors is represented by the internal variations of conditioning factors within slope unit using the descriptive statistics features of mean,standard deviation and range.Thus,slope units-based machine learning models considering internal variations of conditioning factors(variant slope-machine learning)are proposed.The Chongyi County is selected as the case study and is divided into 53,055 slope units.Fifteen original slope unit-based conditioning factors are expanded to 38 slope unit-based conditioning factors through considering their internal variations.Random forest(RF)and multi-layer perceptron(MLP)machine learning models are used to construct variant Slope-RF and Slope-MLP models.Meanwhile,the Slope-RF and Slope-MLP models without considering the internal variations of conditioning factors,and conventional grid units-based machine learning(Grid-RF and MLP)models are built for comparisons through the LSP performance assessments.Results show that the variant Slopemachine learning models have higher LSP performances than Slope-machine learning models;LSP results of variant Slope-machine learning models have stronger directivity and practical application than Grid-machine learning models.It is concluded that slope units extracted by MSS method can be appropriate for LSP modeling,and the heterogeneity of conditioning factors within slope units can more comprehensively reflect the relationships between conditioning factors and landslides.The research results have important reference significance for land use and landslide prevention.
文摘The Indian Himalayan region is frequently experiencing climate change-induced landslides.Thus,landslide susceptibility assessment assumes greater significance for lessening the impact of a landslide hazard.This paper makes an attempt to assess landslide susceptibility in Shimla district of the northwest Indian Himalayan region.It examined the effectiveness of random forest(RF),multilayer perceptron(MLP),sequential minimal optimization regression(SMOreg)and bagging ensemble(B-RF,BSMOreg,B-MLP)models.A landslide inventory map comprising 1052 locations of past landslide occurrences was classified into training(70%)and testing(30%)datasets.The site-specific influencing factors were selected by employing a multicollinearity test.The relationship between past landslide occurrences and influencing factors was established using the frequency ratio method.The effectiveness of machine learning models was verified through performance assessors.The landslide susceptibility maps were validated by the area under the receiver operating characteristic curves(ROC-AUC),accuracy,precision,recall and F1-score.The key performance metrics and map validation demonstrated that the BRF model(correlation coefficient:0.988,mean absolute error:0.010,root mean square error:0.058,relative absolute error:2.964,ROC-AUC:0.947,accuracy:0.778,precision:0.819,recall:0.917 and F-1 score:0.865)outperformed the single classifiers and other bagging ensemble models for landslide susceptibility.The results show that the largest area was found under the very high susceptibility zone(33.87%),followed by the low(27.30%),high(20.68%)and moderate(18.16%)susceptibility zones.The factors,namely average annual rainfall,slope,lithology,soil texture and earthquake magnitude have been identified as the influencing factors for very high landslide susceptibility.Soil texture,lineament density and elevation have been attributed to high and moderate susceptibility.Thus,the study calls for devising suitable landslide mitigation measures in the study area.Structural measures,an immediate response system,community participation and coordination among stakeholders may help lessen the detrimental impact of landslides.The findings from this study could aid decision-makers in mitigating future catastrophes and devising suitable strategies in other geographical regions with similar geological characteristics.
基金supported by grants from the National Natural Science Foundation of China(31771243)the Fok Ying Tong Education Foundation(141113)to Aiguo Chen.
文摘In recent years evidence has emerged suggesting that Mini-basketball training program(MBTP)can be an effec-tive intervention method to improve social communication(SC)impairments and restricted and repetitive beha-viors(RRBs)in preschool children suffering from autism spectrum disorder(ASD).However,there is a considerable degree if interindividual variability concerning these social outcomes and thus not all preschool chil-dren with ASD profit from a MBTP intervention to the same extent.In order to make more accurate predictions which preschool children with ASD can benefit from an MBTP intervention or which preschool children with ASD need additional interventions to achieve behavioral improvements,further research is required.This study aimed to investigate which individual factors of preschool children with ASD can predict MBTP intervention out-comes concerning SC impairments and RRBs.Then,test the performance of machine learning models in predict-ing intervention outcomes based on these factors.Participants were 26 preschool children with ASD who enrolled in a quasi-experiment and received MBTP intervention.Baseline demographic variables(e.g.,age,body,mass index[BMI]),indicators of physicalfitness(e.g.,handgrip strength,balance performance),performance in execu-tive function,severity of ASD symptoms,level of SC impairments,and severity of RRBs were obtained to predict treatment outcomes after MBTP intervention.Machine learning models were established based on support vector machine algorithm were implemented.For comparison,we also employed multiple linear regression models in statistics.Ourfindings suggest that in preschool children with ASD symptomatic severity(r=0.712,p<0.001)and baseline SC impairments(r=0.713,p<0.001)are predictors for intervention outcomes of SC impair-ments.Furthermore,BMI(r=-0.430,p=0.028),symptomatic severity(r=0.656,p<0.001),baseline SC impair-ments(r=0.504,p=0.009)and baseline RRBs(r=0.647,p<0.001)can predict intervention outcomes of RRBs.Statistical models predicted 59.6%of variance in post-treatment SC impairments(MSE=0.455,RMSE=0.675,R2=0.596)and 58.9%of variance in post-treatment RRBs(MSE=0.464,RMSE=0.681,R2=0.589).Machine learning models predicted 83%of variance in post-treatment SC impairments(MSE=0.188,RMSE=0.434,R2=0.83)and 85.9%of variance in post-treatment RRBs(MSE=0.051,RMSE=0.226,R2=0.859),which were better than statistical models.Ourfindings suggest that baseline characteristics such as symptomatic severity of 144 IJMHP,2022,vol.24,no.2 ASD symptoms and SC impairments are important predictors determining MBTP intervention-induced improvements concerning SC impairments and RBBs.Furthermore,the current study revealed that machine learning models can successfully be applied to predict the MBTP intervention-related outcomes in preschool chil-dren with ASD,and performed better than statistical models.Ourfindings can help to inform which preschool children with ASD are most likely to benefit from an MBTP intervention,and they might provide a reference for the development of personalized intervention programs for preschool children with ASD.
文摘BACKGROUND Liver transplantation(LT)is a life-saving intervention for patients with end-stage liver disease.However,the equitable allocation of scarce donor organs remains a formidable challenge.Prognostic tools are pivotal in identifying the most suitable transplant candidates.Traditionally,scoring systems like the model for end-stage liver disease have been instrumental in this process.Nevertheless,the landscape of prognostication is undergoing a transformation with the integration of machine learning(ML)and artificial intelligence models.AIM To assess the utility of ML models in prognostication for LT,comparing their performance and reliability to established traditional scoring systems.METHODS Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines,we conducted a thorough and standardized literature search using the PubMed/MEDLINE database.Our search imposed no restrictions on publication year,age,or gender.Exclusion criteria encompassed non-English studies,review articles,case reports,conference papers,studies with missing data,or those exhibiting evident methodological flaws.RESULTS Our search yielded a total of 64 articles,with 23 meeting the inclusion criteria.Among the selected studies,60.8%originated from the United States and China combined.Only one pediatric study met the criteria.Notably,91%of the studies were published within the past five years.ML models consistently demonstrated satisfactory to excellent area under the receiver operating characteristic curve values(ranging from 0.6 to 1)across all studies,surpassing the performance of traditional scoring systems.Random forest exhibited superior predictive capabilities for 90-d mortality following LT,sepsis,and acute kidney injury(AKI).In contrast,gradient boosting excelled in predicting the risk of graft-versus-host disease,pneumonia,and AKI.CONCLUSION This study underscores the potential of ML models in guiding decisions related to allograft allocation and LT,marking a significant evolution in the field of prognostication.
基金supported by National Natural Science Foundation of China(NSFC)(Nos.61806087,61902158).
文摘This study employs nine distinct deep learning models to categorize 12,444 blood cell images and automatically extract from them relevant information with an accuracy that is beyond that achievable with traditional techniques.The work is intended to improve current methods for the assessment of human health through measurement of the distribution of four types of blood cells,namely,eosinophils,neutrophils,monocytes,and lymphocytes,known for their relationship with human body damage,inflammatory regions,and organ illnesses,in particular,and with the health of the immune system and other hazards,such as cardiovascular disease or infections,more in general.The results of the experiments show that the deep learning models can automatically extract features from the blood cell images and properly classify them with an accuracy of 98%,97%,and 89%,respectively,with regard to the training,verification,and testing of the corresponding datasets.
文摘Forecasting the movement of stock market is a long-time attractive topic. This paper implements different statistical learning models to predict the movement of S&P 500 index. The S&P 500 index is influenced by other important financial indexes across the world such as commodity price and financial technical indicators. This paper systematically investigated four supervised learning models, including Logistic Regression, Gaussian Discriminant Analysis (GDA), Naive Bayes and Support Vector Machine (SVM) in the forecast of S&P 500 index. After several experiments of optimization in features and models, especially the SVM kernel selection and feature selection for different models, this paper concludes that a SVM model with a Radial Basis Function (RBF) kernel can achieve an accuracy rate of 62.51% for the future market trend of the S&P 500 index.
基金funded by the Joint Funds of the National Natural Science Foundation of China(U19B6003)the PetroChina Innovation Foundation(Grant No.2020D5007-0203)it was further supported by the Science Foundation of China University of Petroleum,Beijing(Nos.2462021YXZZ010,2462018QZDX13,and 2462020YXZZ028).
文摘Production performance prediction of tight gas reservoirs is crucial to the estimation of ultimate recovery,which has an important impact on gas field development planning and economic evaluation.Owing to the model’s simplicity,the decline curve analysis method has been widely used to predict production performance.The advancement of deep-learning methods provides an intelligent way of analyzing production performance in tight gas reservoirs.In this paper,a sequence learning method to improve the accuracy and efficiency of tight gas production forecasting is proposed.The sequence learning methods used in production performance analysis herein include the recurrent neural network(RNN),long short-term memory(LSTM)neural network,and gated recurrent unit(GRU)neural network,and their performance in the tight gas reservoir production prediction is investigated and compared.To further improve the performance of the sequence learning method,the hyperparameters in the sequence learning methods are optimized through a particle swarm optimization algorithm,which can greatly simplify the optimization process of the neural network model in an automated manner.Results show that the optimized GRU and RNN models have more compact neural network structures than the LSTM model and that the GRU is more efficiently trained.The predictive performance of LSTM and GRU is similar,and both are better than the RNN and the decline curve analysis model and thus can be used to predict tight gas production.
基金Program of Science and Technology Department of Sichuan Province(2022YFS0541-02)Program of Heavy Rain and Drought-flood Disasters in Plateau and Basin Key Laboratory of Sichuan Province(SCQXKJQN202121)Innovative Development Program of the China Meteorological Administration(CXFZ2021Z007)。
文摘Machine learning models were used to improve the accuracy of China Meteorological Administration Multisource Precipitation Analysis System(CMPAS)in complex terrain areas by combining rain gauge precipitation with topographic factors like altitude,slope,slope direction,slope variability,surface roughness,and meteorological factors like temperature and wind speed.The results of the correction demonstrated that the ensemble learning method has a considerably corrective effect and the three methods(Random Forest,AdaBoost,and Bagging)adopted in the study had similar results.The mean bias between CMPAS and 85%of automatic weather stations has dropped by more than 30%.The plateau region displays the largest accuracy increase,the winter season shows the greatest error reduction,and decreasing precipitation improves the correction outcome.Additionally,the heavy precipitation process’precision has improved to some degree.For individual stations,the revised CMPAS error fluctuation range is significantly reduced.
基金supported by Science Foundation of China University of Petroleum,Beijing(No.2462021BJRC005)Key Technologies of Mahu Conglomerate Reservoir(ZLZX2020-01-04).
文摘Unconventional reservoirs have become the main alternative for increasing oil and gas reserves around the world. Owing to their ultralow permeability properties and special pore structure, hydraulic fracturing technology is necessary to realize the efficient development and economic management of unconventional resources. To maximize the production capacity of wells, several fracture parameters, including fracture number, length, width, conductivity, and spacing, need to be optimized effectively. The optimization of hydraulic fracture parameters in shale gas reservoirs generally demands intensive computations owing to the necessity of numerous physicalmodel simulations. This study proposes a machine learning (ML)–assisted global optimization framework to rapidly obtain optimal fracture parameters. We employed three supervised ML models, including the radialbasis function, K-nearest neighbor, and multilayer perceptron, to emulate the relationship between fracture parameters and shale gas productivity for multistage fractured horizontal wells. Firstly, several forward shale gas simulations with embedded discrete fracture models generate training samples. Then, the samples are divided into training and testing samples to train these ML models and optimize network hyper parameters, respectively. Finally, the trained ML models are combined with an intelligent differential evolution algorithm to optimize the fracture parameters. This novel method has been applied to a naturally fractured reservoir model based on the real-field Barnett shale formation. The obtained results are compared with those of conventional optimizations with high-fidelity models. The results confirm the superiority of the proposed method owing to its very low computational cost. The use of ML modeling technology and an intelligent optimization algorithm could greatly contribute to simulation optimization and design, prompting progress in the intelligent development of unconventional oil and gas reservoirs in China.
基金funded through India Meteorological Department,New Delhi,India under the Forecasting Agricultural output using Space,Agrometeorol ogy and Land based observations(FASAL)project and fund number:No.ASC/FASAL/KT-11/01/HQ-2010.
文摘Background Cotton is one of the most important commercial crops after food crops,especially in countries like India,where it’s grown extensively under rainfed conditions.Because of its usage in multiple industries,such as textile,medicine,and automobile industries,it has greater commercial importance.The crop’s performance is greatly influenced by prevailing weather dynamics.As climate changes,assessing how weather changes affect crop performance is essential.Among various techniques that are available,crop models are the most effective and widely used tools for predicting yields.Results This study compares statistical and machine learning models to assess their ability to predict cotton yield across major producing districts of Karnataka,India,utilizing a long-term dataset spanning from 1990 to 2023 that includes yield and weather factors.The artificial neural networks(ANNs)performed superiorly with acceptable yield deviations ranging within±10%during both vegetative stage(F1)and mid stage(F2)for cotton.The model evaluation metrics such as root mean square error(RMSE),normalized root mean square error(nRMSE),and modelling efficiency(EF)were also within the acceptance limits in most districts.Furthermore,the tested ANN model was used to assess the importance of the dominant weather factors influencing crop yield in each district.Specifically,the use of morning relative humidity as an individual parameter and its interaction with maximum and minimum tempera-ture had a major influence on cotton yield in most of the yield predicted districts.These differences highlighted the differential interactions of weather factors in each district for cotton yield formation,highlighting individual response of each weather factor under different soils and management conditions over the major cotton growing districts of Karnataka.Conclusions Compared with statistical models,machine learning models such as ANNs proved higher efficiency in forecasting the cotton yield due to their ability to consider the interactive effects of weather factors on yield forma-tion at different growth stages.This highlights the best suitability of ANNs for yield forecasting in rainfed conditions and for the study on relative impacts of weather factors on yield.Thus,the study aims to provide valuable insights to support stakeholders in planning effective crop management strategies and formulating relevant policies.
基金Supported by the Chongqing Social Science Planning Project(Grant Number 2020PY48)funded by the Chongqing Federation of Social Sciencethe Joint Project of Chongqing Science and Technology Bureau and Health Commission(Grant Number 2020NCPZX03)funded by the Chongqing Science and Technology Bureau and Chongqing Health Commission of China.
文摘Introduction:Clinical manifestations are essential for early diagnosis of influenza-like illness(ILI).Machine learning models for influenza prediction were developed and a new ILI definition was introduced.Methods:A retrospective cohort study was conducted at three hospitals in southwest China during June 2022 and May 2023.Artificial intelligence was used to extract variables from medical records and XGBOOST algorithm was used to develop prediction models for the total population and three age subgroups.A new ILI definition was introduced based on the optimal model and its performance was compared with WHO,China CDC,and USA CDC definitions.Results:Totally 200,135 patients were included.4,249(36.2%)were confirmed influenza.The predictors of the optimal model included epidemiological characteristics,important symptoms and signs,and age for the total population[Area under curve(AUC)0.734(0.710–0.750),accuracy 0.689(0.669–0.772)].The new ILI definition was fever(≥37.9℃)with cough or rhinorrhea,and its AUC,sensitivity,and specificity for diagnosing influenza were 0.618(0.598–0.639),0.665 and 0.572,outperformed the WHO,China CDC,and USA CDC definitions(P<0.05).Conclusions:Fever,cough,and rhinorrhea maybe the most important indicators for influenza surveillance.
基金supported by the Technology Development Programme of Department of Science and Technology,Government of India(DST/TDT/TDP-22/2022)。
文摘This research explored a novel multimodal approach for disease management in cauliflower crops.With the rising challenges in sustainable agriculture,the research focused on a patch spraying method to control disease and reduce crop losses and environmental impact.For non-destructive disease assessment,a spectral sensor was used to collect spectral information from diseased and healthy cauliflower parts.The spectral data sets were analyzed using decision tree and support vector machine(SVM)algorithms to identify the most accurate model for distinguishing diseased and healthy plants.The chosen model was integrated with a low-volume sprayer(50-150 L·ha^(-1)),equipped with an electronic control unit for targeted spraying based on sensor-detected regions.The decision tree model achieved 89.9% testing accuracy,while the SVM model achieved 96.7% accuracy using hyperparameters:cost of 10.0 and tolerance of 0.001.The research successfully demonstrated the integration of spectral sensors,machine learning,and targeted spraying technology for precise input application.Additionally,the optimized sprayer achieved a 72.5% reduction in chemical usage and a significant time-saving of 21.0% compared to a standard sprayer for black rot-infested crops.These findings highlight the potential efficiency and resource conservation benefits of innovative sprayer technology in precision agriculture and disease management.
基金supported by the National Research Foundation of Korea grant funded by the Korea government(RS-2023-00217116)。
文摘Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server.Despite rapid progress,federated learning still faces several unsolved challenges.Specifically,communication costs and system heterogeneity,such as nonidentical data distribution,hinder federated learning's progress.Several approaches have recently emerged for federated learning involving heterogeneous clients with varying computational capabilities(namely,heterogeneous federated learning).However,heterogeneous federated learning faces two key challenges:optimising model size and determining client selection ratios.Moreover,efficiently aggregating local models from clients with diverse capabilities is crucial for addressing system heterogeneity and communication efficiency.This paper proposes an evolutionary multiobjective optimisation framework for heterogeneous federated learning(MOHFL)to address these issues.Our approach elegantly formulates and solves a biobjective optimisation problem that minimises communication cost and model error rate.The decision variables in this framework comprise model sizes and client selection ratios for each Q client cluster,yielding a total of 2×Q optimisation parameters to be tuned.We develop a partition-based strategy for MOHFL that segregates clients into clusters based on their communication and computation capabilities.Additionally,we implement an adaptive model sizing mechanism that dynamically assigns appropriate subnetwork architectures to clients based on their computational constraints.We also propose a unified aggregation framework to combine models of varying sizes from heterogeneous clients effectively.Extensive experiments on multiple datasets demonstrate the effectiveness and superiority of our proposed method compared to existing approaches.
文摘The prediction of the Tropical Cyclone(TC)intensity helps the government to take proper precautions and disseminate appropriate warnings to civilians.Intensity prediction for TC is a very challenging task due to its dynamically changing internal and external impact factors.We proposed a system to predict TC intensity using CNN-based ensemble deep-learning models that are trained by both satellite images and numerical data of the TC.This paper presents a thorough examination of several deep-learning models such as CNN,Recurrent Neural Networks(RNN)and transfer learning models(AlexNet and VGG)to determine their effectiveness in forecasting TC intensity.Our focus is on four widely recognized models:AlexNet,VGG16,RNN and,a customized CNN-based ensemble model all of which were trained exclusively on image data,as well as an ensemble model that utilized both image and numerical datasets for training.Our analysis evaluates the performance of each model in terms of the loss incurred.The results provide a comparative assessment of the deep learning models selected and offer insights into their respective prediction loss in the form of Mean Square Error(MSE)as 194 in 100 epochs and execution time 1229 s to forecasting TC intensity.We also emphasize the potential benefits of incorporating both image and numerical data into an ensemble model,which can lead to improved prediction accuracy.This research provides valuable knowledge to the field of meteorology and disaster management,paving the way for more resilient and precise TC intensity forecasting models.
基金the Bridge to the Doctorate:Wisconsin Louis Stokes Alliance for Minority Participation National Science Foundation(NSF)award number HRD-1612530the University of Wisconsin-Madison Graduate Engineering Research Scholars(GERS)fellowship program,and the PPG Coating Innovation Center for financial support for the initial part of this work.The other authors gratefully acknowledge support from the NSF Collaborative Research:Framework:Machine Learning Materials Innovation Infrastructure award number 1931306+1 种基金Lane E.Schultz also acknowledges this award for support for the latter part of this work.Machine learning was performed with the computational resources provided by XSEDE 2.0:Integrating,Enabling and Enhancing National Cyberinfrastructure with Expanding Community Involvement Grant ACI-1548562We thank former and current members of the Informatics Skunkworks at the University of Wisconsin-Madison for their contributions to early aspects of this work:Angelo Cortez,Evelin Yin,Jodie Felice Ritchie,Stanley Tzeng,Avi Sharma,Linxiu Zeng,and Vidit Agrawal.
文摘Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions.In this work,we develop a new and general approach of assessing model domain and demonstrate that our approach provides accurate and meaningful domain designation across multiple model types and material property data sets.Our approach assesses the distance between data in feature space using kernel density estimation,where this distance provides an effective tool for domain determination.We show that chemical groups considered unrelated based on chemical knowledge exhibit significant dissimilarities by our measure.We also show that high measures of dissimilarity are associated with poor model performance(i.e.,high residual magnitudes)and poor estimates of model uncertainty(i.e.,unreliable uncertainty estimation).Automated tools are provided to enable researchers to establish acceptable dissimilarity thresholds to identify whether new predictions of their own machine learning models are in-domain versus out-of-domain.
基金funded by the Electric Power Research Institute(EPRI)under award numbers 10012138 and 10012245support for M.J.Lynch was funded by the NASA Space Technology Graduate Research Opportunities(NSTGRO)under grant number 80NSSC21K1246.M.J.Lynch and K.G.Field would like to acknowledge critical feedback from research group members on content and visuals used within this manuscript.
文摘The integration of machine learning(ML)models enhances the efficiency,affordability,and reliability of feature detection in microscopy,yet their development and applicability are hindered by the dependency on scarce and often flawed manually labeled datasets with a lack of domain awareness.We addressed these challenges by creating a physics-based synthetic image and data generator,resulting in an ML model that achieves comparable precision(0.86),recall(0.63),F1 scores(0.71),and engineering property predictions(R2=0.82)to amodel trained on human-labeled data.We enhanced both models by using feature prediction confidence scores to derive an image-wide confidence metric,enabling simple thresholding to eliminate ambiguous and out-of-domain images,resulting in performance boosts of 5–30%with a filtering-out rate of 25%.Our study demonstrates that synthetic data can eliminate human reliance in ML and provides a means for domain awareness in cases where many feature detections per image are needed.
