The reliability of an Engine Electronic Controller(EEC)attracts attention,which has a critical impact on aircraft engine safety.Reliability assessment is an important part of the design phase.However,the complex compo...The reliability of an Engine Electronic Controller(EEC)attracts attention,which has a critical impact on aircraft engine safety.Reliability assessment is an important part of the design phase.However,the complex composition of EEC and the characteristic of the Phased-Mission System(PMS)lead to the difficulty of assessment.This paper puts forward an advanced approach,considering the complex products and uncertain mission profiles to evaluate the Mean Time Between Failures(MTBF)in the design phase.The failure mechanisms of complex components are deduced by Bayesian Deep Learning(BDL)intelligent algorithm.And copious samples of reliability simulation are solved by cloud computing technology.Based on the result of BDL and cloud computing,simulations are conducted with the Physics of Failure(Po F)theory and Failure Behavior Model(FBM).This reliability assessment approach can evaluate MTBF of electronic products without reference to physical tests.Finally,an EEC is applied to verify the effectiveness and accuracy of the method.展开更多
PM_(2.5)constitutes a complex and diversemixture that significantly impacts the environment,human health,and climate change.However,existing observation and numerical simulation techniques have limitations,such as a l...PM_(2.5)constitutes a complex and diversemixture that significantly impacts the environment,human health,and climate change.However,existing observation and numerical simulation techniques have limitations,such as a lack of data,high acquisition costs,andmultiple uncertainties.These limitations hinder the acquisition of comprehensive information on PM_(2.5)chemical composition and effectively implement refined air pollution protection and control strategies.In this study,we developed an optimal deep learning model to acquire hourly mass concentrations of key PM_(2.5)chemical components without complex chemical analysis.The model was trained using a randomly partitioned multivariate dataset arranged in chronological order,including atmospheric state indicators,which previous studies did not consider.Our results showed that the correlation coefficients of key chemical components were no less than 0.96,and the root mean square errors ranged from 0.20 to 2.11μg/m^(3)for the entire process(training and testing combined).The model accurately captured the temporal characteristics of key chemical components,outperforming typical machine-learning models,previous studies,and global reanalysis datasets(such asModern-Era Retrospective analysis for Research and Applications,Version 2(MERRA-2)and Copernicus Atmosphere Monitoring Service ReAnalysis(CAMSRA)).We also quantified the feature importance using the random forest model,which showed that PM_(2.5),PM_(1),visibility,and temperature were the most influential variables for key chemical components.In conclusion,this study presents a practical approach to accurately obtain chemical composition information that can contribute to filling missing data,improved air pollution monitoring and source identification.This approach has the potential to enhance air pollution control strategies and promote public health and environmental sustainability.展开更多
In recent times,web intelligence(WI)has become a hot research topic,which utilizes Artificial Intelligence(AI)and advanced information technologies on theWeb and Internet.The users post reviews on social media and are...In recent times,web intelligence(WI)has become a hot research topic,which utilizes Artificial Intelligence(AI)and advanced information technologies on theWeb and Internet.The users post reviews on social media and are employed for sentiment analysis(SA),which acts as feedback to business people and government.Proper SA on the reviews helps to enhance the quality of the services and products,however,web intelligence techniques are needed to raise the company profit and user fulfillment.With this motivation,this article introduces a new modified pigeon inspired optimization based feature selection(MPIO-FS)with Bayesian deep learning(BDL),named MPIOBDL model for SA on WI applications.The presented MPIO-BDL model initially involved preprocessing and feature extraction take place using Term Frequency—Inverse Document Frequency(TF-IDF)technique to derive a useful set of information from the user reviews.Besides,the MPIO-FS model is applied for the selection of optimal feature subsets,which helps to enhance classification accuracy and reduce computation complexity.Moreover,the BDL model is employed to allocate the proper class labels of the applied user review data.A comprehensive experimental results analysis highlighted the improved classification efficiency of the presented model.展开更多
This study aims to explore the application of Bayesian analysis based on neural networks and deep learning in data visualization.The research background is that with the increasing amount and complexity of data,tradit...This study aims to explore the application of Bayesian analysis based on neural networks and deep learning in data visualization.The research background is that with the increasing amount and complexity of data,traditional data analysis methods have been unable to meet the needs.Research methods include building neural networks and deep learning models,optimizing and improving them through Bayesian analysis,and applying them to the visualization of large-scale data sets.The results show that the neural network combined with Bayesian analysis and deep learning method can effectively improve the accuracy and efficiency of data visualization,and enhance the intuitiveness and depth of data interpretation.The significance of the research is that it provides a new solution for data visualization in the big data environment and helps to further promote the development and application of data science.展开更多
Abnormalities of the gastrointestinal tract are widespread worldwide today.Generally,an effective way to diagnose these life-threatening diseases is based on endoscopy,which comprises a vast number of images.However,t...Abnormalities of the gastrointestinal tract are widespread worldwide today.Generally,an effective way to diagnose these life-threatening diseases is based on endoscopy,which comprises a vast number of images.However,the main challenge in this area is that the process is time-consuming and fatiguing for a gastroenterologist to examine every image in the set.Thus,this led to the rise of studies on designingAI-based systems to assist physicians in the diagnosis.In several medical imaging tasks,deep learning methods,especially convolutional neural networks(CNNs),have contributed to the stateof-the-art outcomes,where the complicated nonlinear relation between target classes and data can be learned and not limit to hand-crafted features.On the other hand,hyperparameters are commonly set manually,which may take a long time and leave the risk of non-optimal hyperparameters for classification.An effective tool for tuning optimal hyperparameters of deep CNNis Bayesian optimization.However,due to the complexity of the CNN,the network can be regarded as a black-box model where the information stored within it is hard to interpret.Hence,Explainable Artificial Intelligence(XAI)techniques are applied to overcome this issue by interpreting the decisions of the CNNs in such wise the physicians can trust.To play an essential role in real-time medical diagnosis,CNN-based models need to be accurate and interpretable,while the uncertainty must be handled.Therefore,a novel method comprising of three phases is proposed to classify these life-threatening diseases.At first,hyperparameter tuning is performed using Bayesian optimization for two state-of-the-art deep CNNs,and then Darknet53 and InceptionV3 features are extracted from these fine-tunned models.Secondly,XAI techniques are used to interpret which part of the images CNN takes for feature extraction.At last,the features are fused,and uncertainties are handled by selecting entropybased features.The experimental results show that the proposed method outperforms existing methods by achieving an accuracy of 97%based on a Bayesian optimized Support Vector Machine classifier.展开更多
Digital twin self-evolution means that digital twin can fuse online sensor data from physical entity to evolve itself,hence improve credibility of the model and represent the physical entity faithfully.There is an urg...Digital twin self-evolution means that digital twin can fuse online sensor data from physical entity to evolve itself,hence improve credibility of the model and represent the physical entity faithfully.There is an urgent need to address the fundamental theories and techniques on how to build such a self-evolving digital twin system for complex equipment optimization and control.Focused on this problem,integrating Bayesian optimization theory and deep reinforcement learning(DRL),this paper proposes a method to build dynamic self-evolving equipment digital twin system for optimal control.First,considering the complexity of current equipment and real-time requirement of dynamic self-evolution scenario,we design digital twin dynamic self-evolution engine using Bayesian optimization theory,which can continuously integrate real-time sensing data,adapt to the dynamic uncertainty changes of physical equipment,so as to improve the credibility of digital twin.Then,a decision-making agent based on DRL algorithm soft actor-critic is designed,which can interact with equipment digital twin in virtual space.When the digital twin model evolves,the agent follows and continues to learn and update itself through online fine-tuning strategy,so as to continuously improve the equipment optimization control performance.Finally,the feasibility and effectiveness of the proposed method are verified by two simulation cases.展开更多
Smart healthcare integrates an advanced wave of information technology using smart devices to collect health-related medical science data.Such data usually exist in unstructured,noisy,incomplete,and heterogeneous form...Smart healthcare integrates an advanced wave of information technology using smart devices to collect health-related medical science data.Such data usually exist in unstructured,noisy,incomplete,and heterogeneous forms.Annotating these limitations remains an open challenge in deep learning to classify health conditions.In this paper,a long short-term memory(LSTM)based health condition prediction framework is proposed to rectify imbalanced and noisy data and transform it into a useful form to predict accurate health conditions.The imbalanced and scarce data is normalized through coding to gain consistency for accurate results using synthetic minority oversampling technique.The proposed model is optimized and ne-tuned in an end to end manner to select ideal parameters using tree parzen estimator to build a probabilistic model.The patient’s medication is pigeonholed to plot the diabetic condition’s risk factor through an algorithm to classify blood glucose metrics using a modern surveillance error grid method.The proposed model can efciently train,validate,and test noisy data by obtaining consistent results around 90%over the state of the art machine and deep learning techniques and overcoming the insufciency in training data through transfer learning.The overall results of the proposed model are further tested with secondary datasets to verify model sustainability.展开更多
Considering the recent developments in deep learning, it has become increasingly important to verify what methods are valid for the prediction of multivariate time-series data. In this study, we propose a novel method...Considering the recent developments in deep learning, it has become increasingly important to verify what methods are valid for the prediction of multivariate time-series data. In this study, we propose a novel method of time-series prediction employing multiple deep learners combined with a Bayesian network where training data is divided into clusters using K-means clustering. We decided how many clusters are the best for K-means with the Bayesian information criteria. Depending on each cluster, the multiple deep learners are trained. We used three types of deep learners: deep neural network (DNN), recurrent neural network (RNN), and long short-term memory (LSTM). A naive Bayes classifier is used to determine which deep learner is in charge of predicting a particular time-series. Our proposed method will be applied to a set of financial time-series data, the Nikkei Average Stock price, to assess the accuracy of the predictions made. Compared with the conventional method of employing a single deep learner to acquire all the data, it is demonstrated by our proposed method that F-value and accuracy are improved.展开更多
One example of an artificial intelligence ethical dilemma is the autonomous vehicle situation presented by Massachusetts Institute of Technology researchers in the Moral Machine Experiment.To solve such dilemmas,the M...One example of an artificial intelligence ethical dilemma is the autonomous vehicle situation presented by Massachusetts Institute of Technology researchers in the Moral Machine Experiment.To solve such dilemmas,the MIT researchers used a classic statistical method known as the hierarchical Bayesian(HB)model.This paper builds upon previous work for modeling moral decision making,applies a deep learning method to learn human ethics in this context,and compares it to the HB approach.These methods were tested to predict moral decisions of simulated populations of Moral Machine participants.Overall,test results indicate that deep neural networks can be effective in learning the group morality of a population through observation,and outperform the Bayesian model in the cases of model mismatches.展开更多
Sign language recognition can be treated as one of the efficient solu-tions for disabled people to communicate with others.It helps them to convey the required data by the use of sign language with no issues.The lates...Sign language recognition can be treated as one of the efficient solu-tions for disabled people to communicate with others.It helps them to convey the required data by the use of sign language with no issues.The latest develop-ments in computer vision and image processing techniques can be accurately uti-lized for the sign recognition process by disabled people.American Sign Language(ASL)detection was challenging because of the enhancing intraclass similarity and higher complexity.This article develops a new Bayesian Optimiza-tion with Deep Learning-Driven Hand Gesture Recognition Based Sign Language Communication(BODL-HGRSLC)for Disabled People.The BODL-HGRSLC technique aims to recognize the hand gestures for disabled people’s communica-tion.The presented BODL-HGRSLC technique integrates the concepts of compu-ter vision(CV)and DL models.In the presented BODL-HGRSLC technique,a deep convolutional neural network-based residual network(ResNet)model is applied for feature extraction.Besides,the presented BODL-HGRSLC model uses Bayesian optimization for the hyperparameter tuning process.At last,a bidir-ectional gated recurrent unit(BiGRU)model is exploited for the HGR procedure.A wide range of experiments was conducted to demonstrate the enhanced perfor-mance of the presented BODL-HGRSLC model.The comprehensive comparison study reported the improvements of the BODL-HGRSLC model over other DL models with maximum accuracy of 99.75%.展开更多
Fire can cause significant damage to the environment,economy,and human lives.If fire can be detected early,the damage can be minimized.Advances in technology,particularly in computer vision powered by deep learning,ha...Fire can cause significant damage to the environment,economy,and human lives.If fire can be detected early,the damage can be minimized.Advances in technology,particularly in computer vision powered by deep learning,have enabled automated fire detection in images and videos.Several deep learning models have been developed for object detection,including applications in fire and smoke detection.This study focuses on optimizing the training hyperparameters of YOLOv8 andYOLOv10models usingBayesianTuning(BT).Experimental results on the large-scale D-Fire dataset demonstrate that this approach enhances detection performance.Specifically,the proposed approach improves the mean average precision at an Intersection over Union(IoU)threshold of 0.5(mAP50)of the YOLOv8s,YOLOv10s,YOLOv8l,and YOLOv10lmodels by 0.26,0.21,0.84,and 0.63,respectively,compared tomodels trainedwith the default hyperparameters.The performance gains are more pronounced in larger models,YOLOv8l and YOLOv10l,than in their smaller counterparts,YOLOv8s and YOLOv10s.Furthermore,YOLOv8 models consistently outperform YOLOv10,with mAP50 improvements of 0.26 for YOLOv8s over YOLOv10s and 0.65 for YOLOv8l over YOLOv10l when trained with BT.These results establish YOLOv8 as the preferred model for fire detection applications where detection performance is prioritized.展开更多
A brain tumor is a disease in which abnormal cells form a tumor in the brain.They are rare and can take many forms,making them difficult to treat,and the survival rate of affected patients is low.Magnetic resonance im...A brain tumor is a disease in which abnormal cells form a tumor in the brain.They are rare and can take many forms,making them difficult to treat,and the survival rate of affected patients is low.Magnetic resonance imaging(MRI)is a crucial tool for diagnosing and localizing brain tumors.However,themanual interpretation of MRI images is tedious and prone to error.As artificial intelligence advances rapidly,DL techniques are increasingly used in medical imaging to accurately detect and diagnose brain tumors.In this study,we introduce a deep convolutional neural network(DCNN)framework for brain tumor classification that uses EfficientNet-B6 as the backbone architecture and adds additional layers.The model achieved an accuracy of 99.10%on the public Brain Tumor MRI datasets,and we performed an ablation study to determine the optimal batch size,optimizer,loss function,and learning rate to maximize the accuracy and robustness of the model,followed by K-Fold cross-validation and testing the model on an independent dataset,and tuning Hyperparameters with Bayesian Optimization to further enhance the performance.When comparing our model to other deep learning(DL)models such as VGG19,MobileNetv2,ResNet50,InceptionV3,and DenseNet201,aswell as variants of the EfficientNetmodel(B1–B7),the results showthat our proposedmodel outperforms all othermodels.Our investigational results demonstrate superiority in terms of precision,recall/sensitivity,accuracy,specificity,and F1-score.Such innovations can potentially enhance clinical decision-making and patient treatment in neurooncological settings.展开更多
为了提高短期风电功率预测的准确性,提出一种基于贝叶斯优化和特征融合的xLSTM(extended Long Short-Term Memory)-Transformer模型。该模型综合应用长短期记忆(LSTM)网络的时序处理能力和Transformer的自注意力机制的动态特征融合能力...为了提高短期风电功率预测的准确性,提出一种基于贝叶斯优化和特征融合的xLSTM(extended Long Short-Term Memory)-Transformer模型。该模型综合应用长短期记忆(LSTM)网络的时序处理能力和Transformer的自注意力机制的动态特征融合能力。借助贝叶斯优化方法,模型可在较少的迭代次数条件下优化超参数,显著降低模型对计算资源的依赖。实验结果表明,内蒙古某风电场数据集上,与单一的LSTM模型、Transformer模型、门控循环单元(GRU)模型以及未采用贝叶斯优化和特征融合的xLSTM-Transformer模型相比,当步长(LookBack)为4和8时,所提模型的决定系数R2较基准模型平均提升1.2%~11.3%;平均绝对误差(MAE)平均降低12.8%~38.4%;均方根误差(RMSE)平均降低8.6%~35.8%。结果表明,所提模型在短历史输入条件下具有更高的预测精度与稳定性。展开更多
Mineral resource exploration increasingly demands not only accurate prospectivity maps but also reliable measures of confidence to guide high-stakes decisions.In this study,a novel Bayesian deep learning(BDL)framework...Mineral resource exploration increasingly demands not only accurate prospectivity maps but also reliable measures of confidence to guide high-stakes decisions.In this study,a novel Bayesian deep learning(BDL)framework was introduced,which embeds probabilistic inference within a deep neural network to jointly predict mineralization potential and quantify uncertainty.Two posterior approximation strategies,Metropolis-Hastings(MH)sampling and variational inference(VI),are implemented to estimate model weights as distributions rather than as fixed values,enabling decomposition of predictive uncertainty into aleatoric and epistemic components.When applied to eleven ore-controlling features in the Nanling tungsten polymetallic region(China),both MH-based and VI-based BDL models demonstrate strong classification performance while revealing contrasting spatial patterns and uncertainty patterns.Correlation studies across probability bands confirm that MH sampling captures a broader spread of uncertainty at the cost of greater computational demand,while VI delivers greater efficiency but risks underestimating uncertainty.The results highlight trade-offs between accuracy,interpret-ability,and computational load,demonstrating that MH-based BDL offers more robust uncertainty assessments,whereas VI-based BDL places greater emphasis on efficiency.By providing spatially explicit probability and uncertainty maps,this framework advances risk-aware mineral exploration,enabling practitioners to target areas of high potential with low uncertainty and to identify regions warranting additional data acquisition.展开更多
Power transformers,as essential equipment for electricity transmission,may fail due to insulation degradation.Predicting the failure rate of power transformers precisely is beneficial to decision-making.Currently,unce...Power transformers,as essential equipment for electricity transmission,may fail due to insulation degradation.Predicting the failure rate of power transformers precisely is beneficial to decision-making.Currently,uncertainties of the prediction have not been deeply discussed.Besides,prediction accuracy is not high enough.This paper proposes a decomposition-based Bayesian deep learning(BDL)method to predict the failure rate of power transformers.Both the model uncertainty related to distribution of the model's weights and the inherent uncertainty associated with random noise can be captured by BDL.Uncertainties of prediction results are depicted with confidence intervals.Moreover,prediction accuracy is improved using variational mode decomposition(VMD).Numerical experiments have been carried out based on oil chromatographic data of power transformers from the Chongqing grid to validate effectiveness of the proposed method.展开更多
基金supported by the National Natural Science Foundation of China(Nos.61503014 and 61573043)。
文摘The reliability of an Engine Electronic Controller(EEC)attracts attention,which has a critical impact on aircraft engine safety.Reliability assessment is an important part of the design phase.However,the complex composition of EEC and the characteristic of the Phased-Mission System(PMS)lead to the difficulty of assessment.This paper puts forward an advanced approach,considering the complex products and uncertain mission profiles to evaluate the Mean Time Between Failures(MTBF)in the design phase.The failure mechanisms of complex components are deduced by Bayesian Deep Learning(BDL)intelligent algorithm.And copious samples of reliability simulation are solved by cloud computing technology.Based on the result of BDL and cloud computing,simulations are conducted with the Physics of Failure(Po F)theory and Failure Behavior Model(FBM).This reliability assessment approach can evaluate MTBF of electronic products without reference to physical tests.Finally,an EEC is applied to verify the effectiveness and accuracy of the method.
基金supported by the National Key Research and Development Program for Young Scientists of China(No.2022YFC3704000)the National Natural Science Foundation of China(No.42275122)the National Key Scientific and Technological Infrastructure project“Earth System Science Numerical Simulator Facility”(EarthLab).
文摘PM_(2.5)constitutes a complex and diversemixture that significantly impacts the environment,human health,and climate change.However,existing observation and numerical simulation techniques have limitations,such as a lack of data,high acquisition costs,andmultiple uncertainties.These limitations hinder the acquisition of comprehensive information on PM_(2.5)chemical composition and effectively implement refined air pollution protection and control strategies.In this study,we developed an optimal deep learning model to acquire hourly mass concentrations of key PM_(2.5)chemical components without complex chemical analysis.The model was trained using a randomly partitioned multivariate dataset arranged in chronological order,including atmospheric state indicators,which previous studies did not consider.Our results showed that the correlation coefficients of key chemical components were no less than 0.96,and the root mean square errors ranged from 0.20 to 2.11μg/m^(3)for the entire process(training and testing combined).The model accurately captured the temporal characteristics of key chemical components,outperforming typical machine-learning models,previous studies,and global reanalysis datasets(such asModern-Era Retrospective analysis for Research and Applications,Version 2(MERRA-2)and Copernicus Atmosphere Monitoring Service ReAnalysis(CAMSRA)).We also quantified the feature importance using the random forest model,which showed that PM_(2.5),PM_(1),visibility,and temperature were the most influential variables for key chemical components.In conclusion,this study presents a practical approach to accurately obtain chemical composition information that can contribute to filling missing data,improved air pollution monitoring and source identification.This approach has the potential to enhance air pollution control strategies and promote public health and environmental sustainability.
文摘In recent times,web intelligence(WI)has become a hot research topic,which utilizes Artificial Intelligence(AI)and advanced information technologies on theWeb and Internet.The users post reviews on social media and are employed for sentiment analysis(SA),which acts as feedback to business people and government.Proper SA on the reviews helps to enhance the quality of the services and products,however,web intelligence techniques are needed to raise the company profit and user fulfillment.With this motivation,this article introduces a new modified pigeon inspired optimization based feature selection(MPIO-FS)with Bayesian deep learning(BDL),named MPIOBDL model for SA on WI applications.The presented MPIO-BDL model initially involved preprocessing and feature extraction take place using Term Frequency—Inverse Document Frequency(TF-IDF)technique to derive a useful set of information from the user reviews.Besides,the MPIO-FS model is applied for the selection of optimal feature subsets,which helps to enhance classification accuracy and reduce computation complexity.Moreover,the BDL model is employed to allocate the proper class labels of the applied user review data.A comprehensive experimental results analysis highlighted the improved classification efficiency of the presented model.
文摘This study aims to explore the application of Bayesian analysis based on neural networks and deep learning in data visualization.The research background is that with the increasing amount and complexity of data,traditional data analysis methods have been unable to meet the needs.Research methods include building neural networks and deep learning models,optimizing and improving them through Bayesian analysis,and applying them to the visualization of large-scale data sets.The results show that the neural network combined with Bayesian analysis and deep learning method can effectively improve the accuracy and efficiency of data visualization,and enhance the intuitiveness and depth of data interpretation.The significance of the research is that it provides a new solution for data visualization in the big data environment and helps to further promote the development and application of data science.
基金This research was supported by the Universiti Malaya Impact-oriented Interdisciplinary Research Grant Programme(IIRG)-IIRG002C-19HWBUniversiti Malaya Covid-19 Related Special Research Grant(UMCSRG)CSRG008-2020ST and Partnership Grant(RK012-2019)from University of Malaya.
文摘Abnormalities of the gastrointestinal tract are widespread worldwide today.Generally,an effective way to diagnose these life-threatening diseases is based on endoscopy,which comprises a vast number of images.However,the main challenge in this area is that the process is time-consuming and fatiguing for a gastroenterologist to examine every image in the set.Thus,this led to the rise of studies on designingAI-based systems to assist physicians in the diagnosis.In several medical imaging tasks,deep learning methods,especially convolutional neural networks(CNNs),have contributed to the stateof-the-art outcomes,where the complicated nonlinear relation between target classes and data can be learned and not limit to hand-crafted features.On the other hand,hyperparameters are commonly set manually,which may take a long time and leave the risk of non-optimal hyperparameters for classification.An effective tool for tuning optimal hyperparameters of deep CNNis Bayesian optimization.However,due to the complexity of the CNN,the network can be regarded as a black-box model where the information stored within it is hard to interpret.Hence,Explainable Artificial Intelligence(XAI)techniques are applied to overcome this issue by interpreting the decisions of the CNNs in such wise the physicians can trust.To play an essential role in real-time medical diagnosis,CNN-based models need to be accurate and interpretable,while the uncertainty must be handled.Therefore,a novel method comprising of three phases is proposed to classify these life-threatening diseases.At first,hyperparameter tuning is performed using Bayesian optimization for two state-of-the-art deep CNNs,and then Darknet53 and InceptionV3 features are extracted from these fine-tunned models.Secondly,XAI techniques are used to interpret which part of the images CNN takes for feature extraction.At last,the features are fused,and uncertainties are handled by selecting entropybased features.The experimental results show that the proposed method outperforms existing methods by achieving an accuracy of 97%based on a Bayesian optimized Support Vector Machine classifier.
基金supported by the National Natural Science Foundation of China under Grant No.62373026。
文摘Digital twin self-evolution means that digital twin can fuse online sensor data from physical entity to evolve itself,hence improve credibility of the model and represent the physical entity faithfully.There is an urgent need to address the fundamental theories and techniques on how to build such a self-evolving digital twin system for complex equipment optimization and control.Focused on this problem,integrating Bayesian optimization theory and deep reinforcement learning(DRL),this paper proposes a method to build dynamic self-evolving equipment digital twin system for optimal control.First,considering the complexity of current equipment and real-time requirement of dynamic self-evolution scenario,we design digital twin dynamic self-evolution engine using Bayesian optimization theory,which can continuously integrate real-time sensing data,adapt to the dynamic uncertainty changes of physical equipment,so as to improve the credibility of digital twin.Then,a decision-making agent based on DRL algorithm soft actor-critic is designed,which can interact with equipment digital twin in virtual space.When the digital twin model evolves,the agent follows and continues to learn and update itself through online fine-tuning strategy,so as to continuously improve the equipment optimization control performance.Finally,the feasibility and effectiveness of the proposed method are verified by two simulation cases.
基金supported by Researchers Supporting Project number(RSP2020/87),King Saud University,Riyadh,Saudi Arabia.
文摘Smart healthcare integrates an advanced wave of information technology using smart devices to collect health-related medical science data.Such data usually exist in unstructured,noisy,incomplete,and heterogeneous forms.Annotating these limitations remains an open challenge in deep learning to classify health conditions.In this paper,a long short-term memory(LSTM)based health condition prediction framework is proposed to rectify imbalanced and noisy data and transform it into a useful form to predict accurate health conditions.The imbalanced and scarce data is normalized through coding to gain consistency for accurate results using synthetic minority oversampling technique.The proposed model is optimized and ne-tuned in an end to end manner to select ideal parameters using tree parzen estimator to build a probabilistic model.The patient’s medication is pigeonholed to plot the diabetic condition’s risk factor through an algorithm to classify blood glucose metrics using a modern surveillance error grid method.The proposed model can efciently train,validate,and test noisy data by obtaining consistent results around 90%over the state of the art machine and deep learning techniques and overcoming the insufciency in training data through transfer learning.The overall results of the proposed model are further tested with secondary datasets to verify model sustainability.
文摘Considering the recent developments in deep learning, it has become increasingly important to verify what methods are valid for the prediction of multivariate time-series data. In this study, we propose a novel method of time-series prediction employing multiple deep learners combined with a Bayesian network where training data is divided into clusters using K-means clustering. We decided how many clusters are the best for K-means with the Bayesian information criteria. Depending on each cluster, the multiple deep learners are trained. We used three types of deep learners: deep neural network (DNN), recurrent neural network (RNN), and long short-term memory (LSTM). A naive Bayes classifier is used to determine which deep learner is in charge of predicting a particular time-series. Our proposed method will be applied to a set of financial time-series data, the Nikkei Average Stock price, to assess the accuracy of the predictions made. Compared with the conventional method of employing a single deep learner to acquire all the data, it is demonstrated by our proposed method that F-value and accuracy are improved.
文摘One example of an artificial intelligence ethical dilemma is the autonomous vehicle situation presented by Massachusetts Institute of Technology researchers in the Moral Machine Experiment.To solve such dilemmas,the MIT researchers used a classic statistical method known as the hierarchical Bayesian(HB)model.This paper builds upon previous work for modeling moral decision making,applies a deep learning method to learn human ethics in this context,and compares it to the HB approach.These methods were tested to predict moral decisions of simulated populations of Moral Machine participants.Overall,test results indicate that deep neural networks can be effective in learning the group morality of a population through observation,and outperform the Bayesian model in the cases of model mismatches.
基金The authors extend their appreciation to the King Salman centre for Disability Research for funding this work through Research Group no KSRG-2022-017.
文摘Sign language recognition can be treated as one of the efficient solu-tions for disabled people to communicate with others.It helps them to convey the required data by the use of sign language with no issues.The latest develop-ments in computer vision and image processing techniques can be accurately uti-lized for the sign recognition process by disabled people.American Sign Language(ASL)detection was challenging because of the enhancing intraclass similarity and higher complexity.This article develops a new Bayesian Optimiza-tion with Deep Learning-Driven Hand Gesture Recognition Based Sign Language Communication(BODL-HGRSLC)for Disabled People.The BODL-HGRSLC technique aims to recognize the hand gestures for disabled people’s communica-tion.The presented BODL-HGRSLC technique integrates the concepts of compu-ter vision(CV)and DL models.In the presented BODL-HGRSLC technique,a deep convolutional neural network-based residual network(ResNet)model is applied for feature extraction.Besides,the presented BODL-HGRSLC model uses Bayesian optimization for the hyperparameter tuning process.At last,a bidir-ectional gated recurrent unit(BiGRU)model is exploited for the HGR procedure.A wide range of experiments was conducted to demonstrate the enhanced perfor-mance of the presented BODL-HGRSLC model.The comprehensive comparison study reported the improvements of the BODL-HGRSLC model over other DL models with maximum accuracy of 99.75%.
基金supported by the MSIT(Ministry of Science and ICT),Republic of Korea,under the ITRC(Information Technology Research Center)Support Program(IITP-2024-RS-2022-00156354)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation)supported by the Technology Development Program(RS-2023-00264489)funded by the Ministry of SMEs and Startups(MSS,Republic of Korea).
文摘Fire can cause significant damage to the environment,economy,and human lives.If fire can be detected early,the damage can be minimized.Advances in technology,particularly in computer vision powered by deep learning,have enabled automated fire detection in images and videos.Several deep learning models have been developed for object detection,including applications in fire and smoke detection.This study focuses on optimizing the training hyperparameters of YOLOv8 andYOLOv10models usingBayesianTuning(BT).Experimental results on the large-scale D-Fire dataset demonstrate that this approach enhances detection performance.Specifically,the proposed approach improves the mean average precision at an Intersection over Union(IoU)threshold of 0.5(mAP50)of the YOLOv8s,YOLOv10s,YOLOv8l,and YOLOv10lmodels by 0.26,0.21,0.84,and 0.63,respectively,compared tomodels trainedwith the default hyperparameters.The performance gains are more pronounced in larger models,YOLOv8l and YOLOv10l,than in their smaller counterparts,YOLOv8s and YOLOv10s.Furthermore,YOLOv8 models consistently outperform YOLOv10,with mAP50 improvements of 0.26 for YOLOv8s over YOLOv10s and 0.65 for YOLOv8l over YOLOv10l when trained with BT.These results establish YOLOv8 as the preferred model for fire detection applications where detection performance is prioritized.
基金funded by the King Saud University,Riyadh,Saudi Arabia,for funding this work through the Researchers Supporting Research Funding program,(ORF-2025-1268).
文摘A brain tumor is a disease in which abnormal cells form a tumor in the brain.They are rare and can take many forms,making them difficult to treat,and the survival rate of affected patients is low.Magnetic resonance imaging(MRI)is a crucial tool for diagnosing and localizing brain tumors.However,themanual interpretation of MRI images is tedious and prone to error.As artificial intelligence advances rapidly,DL techniques are increasingly used in medical imaging to accurately detect and diagnose brain tumors.In this study,we introduce a deep convolutional neural network(DCNN)framework for brain tumor classification that uses EfficientNet-B6 as the backbone architecture and adds additional layers.The model achieved an accuracy of 99.10%on the public Brain Tumor MRI datasets,and we performed an ablation study to determine the optimal batch size,optimizer,loss function,and learning rate to maximize the accuracy and robustness of the model,followed by K-Fold cross-validation and testing the model on an independent dataset,and tuning Hyperparameters with Bayesian Optimization to further enhance the performance.When comparing our model to other deep learning(DL)models such as VGG19,MobileNetv2,ResNet50,InceptionV3,and DenseNet201,aswell as variants of the EfficientNetmodel(B1–B7),the results showthat our proposedmodel outperforms all othermodels.Our investigational results demonstrate superiority in terms of precision,recall/sensitivity,accuracy,specificity,and F1-score.Such innovations can potentially enhance clinical decision-making and patient treatment in neurooncological settings.
文摘为了提高短期风电功率预测的准确性,提出一种基于贝叶斯优化和特征融合的xLSTM(extended Long Short-Term Memory)-Transformer模型。该模型综合应用长短期记忆(LSTM)网络的时序处理能力和Transformer的自注意力机制的动态特征融合能力。借助贝叶斯优化方法,模型可在较少的迭代次数条件下优化超参数,显著降低模型对计算资源的依赖。实验结果表明,内蒙古某风电场数据集上,与单一的LSTM模型、Transformer模型、门控循环单元(GRU)模型以及未采用贝叶斯优化和特征融合的xLSTM-Transformer模型相比,当步长(LookBack)为4和8时,所提模型的决定系数R2较基准模型平均提升1.2%~11.3%;平均绝对误差(MAE)平均降低12.8%~38.4%;均方根误差(RMSE)平均降低8.6%~35.8%。结果表明,所提模型在短历史输入条件下具有更高的预测精度与稳定性。
基金supported by the Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project(No.2024ZD1002400).
文摘Mineral resource exploration increasingly demands not only accurate prospectivity maps but also reliable measures of confidence to guide high-stakes decisions.In this study,a novel Bayesian deep learning(BDL)framework was introduced,which embeds probabilistic inference within a deep neural network to jointly predict mineralization potential and quantify uncertainty.Two posterior approximation strategies,Metropolis-Hastings(MH)sampling and variational inference(VI),are implemented to estimate model weights as distributions rather than as fixed values,enabling decomposition of predictive uncertainty into aleatoric and epistemic components.When applied to eleven ore-controlling features in the Nanling tungsten polymetallic region(China),both MH-based and VI-based BDL models demonstrate strong classification performance while revealing contrasting spatial patterns and uncertainty patterns.Correlation studies across probability bands confirm that MH sampling captures a broader spread of uncertainty at the cost of greater computational demand,while VI delivers greater efficiency but risks underestimating uncertainty.The results highlight trade-offs between accuracy,interpret-ability,and computational load,demonstrating that MH-based BDL offers more robust uncertainty assessments,whereas VI-based BDL places greater emphasis on efficiency.By providing spatially explicit probability and uncertainty maps,this framework advances risk-aware mineral exploration,enabling practitioners to target areas of high potential with low uncertainty and to identify regions warranting additional data acquisition.
文摘Power transformers,as essential equipment for electricity transmission,may fail due to insulation degradation.Predicting the failure rate of power transformers precisely is beneficial to decision-making.Currently,uncertainties of the prediction have not been deeply discussed.Besides,prediction accuracy is not high enough.This paper proposes a decomposition-based Bayesian deep learning(BDL)method to predict the failure rate of power transformers.Both the model uncertainty related to distribution of the model's weights and the inherent uncertainty associated with random noise can be captured by BDL.Uncertainties of prediction results are depicted with confidence intervals.Moreover,prediction accuracy is improved using variational mode decomposition(VMD).Numerical experiments have been carried out based on oil chromatographic data of power transformers from the Chongqing grid to validate effectiveness of the proposed method.
