Dear Editor,This letter proposes a deep synchronization control(DSC) method to synchronize grid-forming converters with power grids. The method involves constructing a novel controller for grid-forming converters base...Dear Editor,This letter proposes a deep synchronization control(DSC) method to synchronize grid-forming converters with power grids. The method involves constructing a novel controller for grid-forming converters based on the stable deep dynamics model. To enhance the performance of the controller, the dynamics model is optimized within the deep reinforcement learning(DRL) framework. Simulation results verify that the proposed method can reduce frequency deviation and improve active power responses.展开更多
Accurate detection of small objects is critically important in high-stakes applications such as military reconnaissance and emergency rescue.However,low resolution,occlusion,and background interference make small obje...Accurate detection of small objects is critically important in high-stakes applications such as military reconnaissance and emergency rescue.However,low resolution,occlusion,and background interference make small object detection a complex and demanding task.One effective approach to overcome these issues is the integration of multimodal image data to enhance detection capabilities.This paper proposes a novel small object detection method that utilizes three types of multimodal image combinations,such as Hyperspectral-Multispectral(HSMS),Hyperspectral-Synthetic Aperture Radar(HS-SAR),and HS-SAR-Digital Surface Model(HS-SAR-DSM).The detection process is done by the proposed Jaccard Deep Q-Net(JDQN),which integrates the Jaccard similarity measure with a Deep Q-Network(DQN)using regression modeling.To produce the final output,a Deep Maxout Network(DMN)is employed to fuse the detection results obtained from each modality.The effectiveness of the proposed JDQN is validated using performance metrics,such as accuracy,Mean Squared Error(MSE),precision,and Root Mean Squared Error(RMSE).Experimental results demonstrate that the proposed JDQN method outperforms existing approaches,achieving the highest accuracy of 0.907,a precision of 0.904,the lowest normalized MSE of 0.279,and a normalized RMSE of 0.528.展开更多
Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of data.Recently,both deep learning and ensem...Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of data.Recently,both deep learning and ensemble learning have been used to recognize underlying structures and patterns from high-level features to make predictions/decisions.With the growth in popularity of deep learning and ensemble learning algorithms,they have received significant attention from both scientists and the industrial community due to their superior ability to learn features from big data.Ensemble deep learning has exhibited significant performance in enhancing learning generalization through the use of multiple deep learning algorithms.Although ensemble deep learning has large quantities of training parameters,which results in time and space overheads,it performs much better than traditional ensemble learning.Ensemble deep learning has been successfully used in several areas,such as bioinformatics,finance,and health care.In this paper,we review and investigate recent ensemble deep learning algorithms and techniques in health care domains,medical imaging,health care data analytics,genomics,diagnosis,disease prevention,and drug discovery.We cover several widely used deep learning algorithms along with their architectures,including deep neural networks(DNNs),convolutional neural networks(CNNs),recurrent neural networks(RNNs),and generative adversarial networks(GANs).Common healthcare tasks,such as medical imaging,electronic health records,and genomics,are also demonstrated.Furthermore,in this review,the challenges inherent in reducing the burden on the healthcare system are discussed and explored.Finally,future directions and opportunities for enhancing healthcare model performance are discussed.展开更多
This paper provides a comprehensive bibliometric exposition on deepfake research,exploring the intersection of artificial intelligence and deepfakes as well as international collaborations,prominent researchers,organi...This paper provides a comprehensive bibliometric exposition on deepfake research,exploring the intersection of artificial intelligence and deepfakes as well as international collaborations,prominent researchers,organizations,institutions,publications,and key themes.We performed a search on theWeb of Science(WoS)database,focusing on Artificial Intelligence and Deepfakes,and filtered the results across 21 research areas,yielding 1412 articles.Using VOSviewer visualization tool,we analyzed thisWoS data through keyword co-occurrence graphs,emphasizing on four prominent research themes.Compared with existing bibliometric papers on deepfakes,this paper proceeds to identify and discuss some of the highly cited papers within these themes:deepfake detection,feature extraction,face recognition,and forensics.The discussion highlights key challenges and advancements in deepfake research.Furthermore,this paper also discusses pressing issues surrounding deepfakes such as security,regulation,and datasets.We also provide an analysis of another exhaustive search on Scopus database focusing solely on Deepfakes(while not excluding AI)revealing deep learning as the predominant keyword,underscoring AI’s central role in deepfake research.This comprehensive analysis,encompassing over 500 keywords from 8790 articles,uncovered a wide range of methods,implications,applications,concerns,requirements,challenges,models,tools,datasets,and modalities related to deepfakes.Finally,a discussion on recommendations for policymakers,researchers,and other stakeholders is also provided.展开更多
On February 20,2025,China National Petroleum Corporation announced that China's first ultra-deep scientific exploration well-Shenditake 1 Well-successfully reached a depth of 10910 m underground(Fig.1).Deep Earth ...On February 20,2025,China National Petroleum Corporation announced that China's first ultra-deep scientific exploration well-Shenditake 1 Well-successfully reached a depth of 10910 m underground(Fig.1).Deep Earth Towerke 1 Well is located in the heart of the Taklamakan Desert in the Xinjiang Uyghur Autonomous Region,within the territory of Shaya County.It has become the deepest vertical well in Asia and the second deepest in the world.The well has successively set five major engineering records:The deepest global tailpipe cementing,the deepest global cable imaging logging,the fastest global onshore drilling to exceed 10000 m,the deepest direct well drilling in Asia,and the deepest onshore coring in Asia.This marks another major breakthrough for China in the field of“Deep Earth”exploration,following its achievements in“Deep Space”and“Deep Sea.”展开更多
Automated classification of retinal fundus images is essential for identifying eye diseases,though there is earlier research on applying deep learning models designed especially for detecting tessellation in retinal f...Automated classification of retinal fundus images is essential for identifying eye diseases,though there is earlier research on applying deep learning models designed especially for detecting tessellation in retinal fundus images.This study classifies 4 classes of retinal fundus images with 3 diseased fundus images and 1 normal fundus image,by creating a refined VGG16 model to categorize fundus pictures into tessellated,normal,myopia,and choroidal neovascularization groups.The approach utilizes a VGG16 architecture that has been altered with unique fully connected layers and regularization using dropouts,along with data augmentation techniques(rotation,flip,and rescale)on a dataset of 302 photos.Training involves class weighting and critical callbacks(early halting,learning rate reduction,checkpointing)to maximize performance.Gains in accuracy(93.42%training,77.5%validation)and improved class-specific F1 scores are attained.Grad-CAM’s Explainable AI(XAI)highlights areas of the images that are important for each categorization,making it interpretable for better understanding of medical experts.These results highlight the model’s potential as a helpful diagnostic tool in ophthalmology,providing a clear and practical method for the early identification and categorization of retinal disorders,especially in cases such as tessellated fundus images.展开更多
This reviewpresents a comprehensive technical analysis of deep learning(DL)methodologies in biomedical signal processing,focusing on architectural innovations,experimental validation,and evaluation frameworks.We syste...This reviewpresents a comprehensive technical analysis of deep learning(DL)methodologies in biomedical signal processing,focusing on architectural innovations,experimental validation,and evaluation frameworks.We systematically evaluate key deep learning architectures including convolutional neural networks(CNNs),recurrent neural networks(RNNs),transformer-based models,and hybrid systems across critical tasks such as arrhythmia classification,seizure detection,and anomaly segmentation.The study dissects preprocessing techniques(e.g.,wavelet denoising,spectral normalization)and feature extraction strategies(time-frequency analysis,attention mechanisms),demonstrating their impact on model accuracy,noise robustness,and computational efficiency.Experimental results underscore the superiority of deep learning over traditional methods,particularly in automated feature extraction,real-time processing,cross-modal generalization,and achieving up to a 15%increase in classification accuracy and enhanced noise resilience across electrocardiogram(ECG),electroencephalogram(EEG),and electromyogram(EMG)signals.Performance is rigorously benchmarked using precision,recall,F1-scores,area under the receiver operating characteristic curve(AUC-ROC),and computational complexitymetrics,providing a unified framework for comparing model efficacy.Thesurvey addresses persistent challenges:synthetic data generationmitigates limited training samples,interpretability tools(e.g.,Gradient-weighted Class Activation Mapping(Grad-CAM),Shapley values)resolve model opacity,and federated learning ensures privacy-compliant deployments.Distinguished from prior reviews,this work offers a structured taxonomy of deep learning architectures,integrates emerging paradigms like transformers and domain-specific attention mechanisms,and evaluates preprocessing pipelines for spectral-temporal trade-offs.It advances the field by bridging technical advancements with clinical needs,such as scalability in real-world settings(e.g.,wearable devices)and regulatory alignment with theHealth Insurance Portability and Accountability Act(HIPAA)and General Data Protection Regulation(GDPR).By synthesizing technical rigor,ethical considerations,and actionable guidelines for model selection,this survey establishes a holistic reference for developing robust,interpretable biomedical artificial intelligence(AI)systems,accelerating their translation into personalized and equitable healthcare solutions.展开更多
Aiming at the problem that the bit error rate(BER)of asymmetrically clipped optical orthogonal frequency division multiplexing(ACO-OFDM)space optical communication system is significantly affected by different turbule...Aiming at the problem that the bit error rate(BER)of asymmetrically clipped optical orthogonal frequency division multiplexing(ACO-OFDM)space optical communication system is significantly affected by different turbulence intensities,the deep learning technique is proposed to the polarization code decoding in ACO-OFDM space optical communication system.Moreover,this system realizes the polarization code decoding and signal demodulation without frequency conduction with superior performance and robustness compared with the performance of traditional decoder.Simulations under different turbulence intensities as well as different mapping orders show that the convolutional neural network(CNN)decoder trained under weak-medium-strong turbulence atmospheric channels achieves a performance improvement of about 10^(2)compared to the conventional decoder at 4-quadrature amplitude modulation(4QAM),and the BERs for both 16QAM and 64QAM are in between those of the conventional decoder.展开更多
The deep sea holds vital resources and spatial potential for future human survival and development,reflecting the common interests and concerns of all mankind.Amidst unprecedented global transformations in a hundred y...The deep sea holds vital resources and spatial potential for future human survival and development,reflecting the common interests and concerns of all mankind.Amidst unprecedented global transformations in a hundred years,the deep sea has emerged as a critical area of international competition and serves as a new frontier for resource extraction,a strategic space for military competition,and a contested space for great power rivalry and rule-making.展开更多
The warming and thawing of permafrost are the primary factors that impact the stability of embankments in cold regions.However,due to uncertainties in thermal boundaries and soil properties,the stochastic modeling of ...The warming and thawing of permafrost are the primary factors that impact the stability of embankments in cold regions.However,due to uncertainties in thermal boundaries and soil properties,the stochastic modeling of thermal regimes is challenging and computationally expensive.To address this,we propose a knowledge-integrated deep learning method for predicting the stochastic thermal regime of embankments in permafrost regions.Geotechnical knowledge is embedded in the training data through numerical modeling,while the neural network learns the mapping from the thermal boundary and soil property fields to the temperature field.The effectiveness of our method is verified in comparison with monitoring data and numerical analysis results.Experimental results show that the proposed method achieves good accuracy with small coefficient of variation.It still provides satisfactory accuracy as the coefficient of variation increases.The proposed knowledge-integrated deep learning method provides an efficient approach to predict the stochastic thermal regime of heterogeneous embankments.It can also be used in other permafrost engineering investigations that require stochastic numerical modeling.展开更多
Layered rock masses represent complex geological formations commonly encountered in the surrounding rock of deep engineering excavations(Hou et al.,2019;Xu et al.,2017;Yang C H et al.,2009;Xian and Tan,1989).These roc...Layered rock masses represent complex geological formations commonly encountered in the surrounding rock of deep engineering excavations(Hou et al.,2019;Xu et al.,2017;Yang C H et al.,2009;Xian and Tan,1989).These rock masses are predominantly composed of sedimentary,para-metamorphic,and volcanic rock types,characterized by a set of prominent,primary bedding structural planes(layers)exhibiting relatively consistent orientations and significant spatial continuity.展开更多
The Virtual Power Plant(VPP),as an innovative power management architecture,achieves flexible dispatch and resource optimization of power systems by integrating distributed energy resources.However,due to significant ...The Virtual Power Plant(VPP),as an innovative power management architecture,achieves flexible dispatch and resource optimization of power systems by integrating distributed energy resources.However,due to significant differences in operational costs and flexibility of various types of generation resources,as well as the volatility and uncertainty of renewable energy sources(such as wind and solar power)and the complex variability of load demand,the scheduling optimization of virtual power plants has become a critical issue that needs to be addressed.To solve this,this paper proposes an intelligent scheduling method for virtual power plants based on Deep Reinforcement Learning(DRL),utilizing Deep Q-Networks(DQN)for real-time optimization scheduling of dynamic peaking unit(DPU)and stable baseload unit(SBU)in the virtual power plant.By modeling the scheduling problem as a Markov Decision Process(MDP)and designing an optimization objective function that integrates both performance and cost,the scheduling efficiency and economic performance of the virtual power plant are significantly improved.Simulation results show that,compared with traditional scheduling methods and other deep reinforcement learning algorithms,the proposed method demonstrates significant advantages in key performance indicators:response time is shortened by up to 34%,task success rate is increased by up to 46%,and costs are reduced by approximately 26%.Experimental results verify the efficiency and scalability of the method under complex load environments and the volatility of renewable energy,providing strong technical support for the intelligent scheduling of virtual power plants.展开更多
Inferring phylogenetic trees from molecular sequences is a cornerstone of evolutionary biology.Many standard phylogenetic methods(such as maximum-likelihood[ML])rely on explicit models of sequence evolution and thus o...Inferring phylogenetic trees from molecular sequences is a cornerstone of evolutionary biology.Many standard phylogenetic methods(such as maximum-likelihood[ML])rely on explicit models of sequence evolution and thus often suffer from model misspecification or inadequacy.The on-rising deep learning(DL)techniques offer a powerful alternative.Deep learning employs multi-layered artificial neural networks to progressively transform input data into more abstract and complex representations.DL methods can autonomously uncover meaningful patterns from data,thereby bypassing potential biases introduced by predefined features(Franklin,2005;Murphy,2012).Recent efforts have aimed to apply deep neural networks(DNNs)to phylogenetics,with a growing number of applications in tree reconstruction(Suvorov et al.,2020;Zou et al.,2020;Nesterenko et al.,2022;Smith and Hahn,2023;Wang et al.,2023),substitution model selection(Abadi et al.,2020;Burgstaller-Muehlbacher et al.,2023),and diversification rate inference(Voznica et al.,2022;Lajaaiti et al.,2023;Lambert et al.,2023).In phylogenetic tree reconstruction,PhyDL(Zou et al.,2020)and Tree_learning(Suvorov et al.,2020)are two notable DNN-based programs designed to infer unrooted quartet trees directly from alignments of four amino acid(AA)and DNA sequences,respectively.展开更多
With the proposal and implementation of the“Belt and Road”initiative,economic development requires the drive of a large number of talents and real industries.Local governments along the route also encourage universi...With the proposal and implementation of the“Belt and Road”initiative,economic development requires the drive of a large number of talents and real industries.Local governments along the route also encourage universities and enterprises to carry out high-level school-enterprise cooperation to promote the effective sharing of education and economy,thus ensuring the development of the regional economy.In order to better adapt to relevant national policies,promote regional economic development,and supply high-quality and skilled talents to society,higher vocational colleges should strengthen education reform,introduce the school-enterprise cooperation mechanism,achieve the deep integration between schools and enterprises,and promote regional economic development.Based on this,this paper analyzes and studies the deep cooperation model between higher vocational colleges and enterprises under the“Belt and Road”initiative for reference.展开更多
基金supported in part by the National Natural Science Foundation of China(62033005,62273270)the Natural Science Foundation of Shaanxi Province(2023JC-XJ17)
文摘Dear Editor,This letter proposes a deep synchronization control(DSC) method to synchronize grid-forming converters with power grids. The method involves constructing a novel controller for grid-forming converters based on the stable deep dynamics model. To enhance the performance of the controller, the dynamics model is optimized within the deep reinforcement learning(DRL) framework. Simulation results verify that the proposed method can reduce frequency deviation and improve active power responses.
文摘Accurate detection of small objects is critically important in high-stakes applications such as military reconnaissance and emergency rescue.However,low resolution,occlusion,and background interference make small object detection a complex and demanding task.One effective approach to overcome these issues is the integration of multimodal image data to enhance detection capabilities.This paper proposes a novel small object detection method that utilizes three types of multimodal image combinations,such as Hyperspectral-Multispectral(HSMS),Hyperspectral-Synthetic Aperture Radar(HS-SAR),and HS-SAR-Digital Surface Model(HS-SAR-DSM).The detection process is done by the proposed Jaccard Deep Q-Net(JDQN),which integrates the Jaccard similarity measure with a Deep Q-Network(DQN)using regression modeling.To produce the final output,a Deep Maxout Network(DMN)is employed to fuse the detection results obtained from each modality.The effectiveness of the proposed JDQN is validated using performance metrics,such as accuracy,Mean Squared Error(MSE),precision,and Root Mean Squared Error(RMSE).Experimental results demonstrate that the proposed JDQN method outperforms existing approaches,achieving the highest accuracy of 0.907,a precision of 0.904,the lowest normalized MSE of 0.279,and a normalized RMSE of 0.528.
基金funded by Taif University,Saudi Arabia,project No.(TU-DSPP-2024-263).
文摘Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of data.Recently,both deep learning and ensemble learning have been used to recognize underlying structures and patterns from high-level features to make predictions/decisions.With the growth in popularity of deep learning and ensemble learning algorithms,they have received significant attention from both scientists and the industrial community due to their superior ability to learn features from big data.Ensemble deep learning has exhibited significant performance in enhancing learning generalization through the use of multiple deep learning algorithms.Although ensemble deep learning has large quantities of training parameters,which results in time and space overheads,it performs much better than traditional ensemble learning.Ensemble deep learning has been successfully used in several areas,such as bioinformatics,finance,and health care.In this paper,we review and investigate recent ensemble deep learning algorithms and techniques in health care domains,medical imaging,health care data analytics,genomics,diagnosis,disease prevention,and drug discovery.We cover several widely used deep learning algorithms along with their architectures,including deep neural networks(DNNs),convolutional neural networks(CNNs),recurrent neural networks(RNNs),and generative adversarial networks(GANs).Common healthcare tasks,such as medical imaging,electronic health records,and genomics,are also demonstrated.Furthermore,in this review,the challenges inherent in reducing the burden on the healthcare system are discussed and explored.Finally,future directions and opportunities for enhancing healthcare model performance are discussed.
文摘This paper provides a comprehensive bibliometric exposition on deepfake research,exploring the intersection of artificial intelligence and deepfakes as well as international collaborations,prominent researchers,organizations,institutions,publications,and key themes.We performed a search on theWeb of Science(WoS)database,focusing on Artificial Intelligence and Deepfakes,and filtered the results across 21 research areas,yielding 1412 articles.Using VOSviewer visualization tool,we analyzed thisWoS data through keyword co-occurrence graphs,emphasizing on four prominent research themes.Compared with existing bibliometric papers on deepfakes,this paper proceeds to identify and discuss some of the highly cited papers within these themes:deepfake detection,feature extraction,face recognition,and forensics.The discussion highlights key challenges and advancements in deepfake research.Furthermore,this paper also discusses pressing issues surrounding deepfakes such as security,regulation,and datasets.We also provide an analysis of another exhaustive search on Scopus database focusing solely on Deepfakes(while not excluding AI)revealing deep learning as the predominant keyword,underscoring AI’s central role in deepfake research.This comprehensive analysis,encompassing over 500 keywords from 8790 articles,uncovered a wide range of methods,implications,applications,concerns,requirements,challenges,models,tools,datasets,and modalities related to deepfakes.Finally,a discussion on recommendations for policymakers,researchers,and other stakeholders is also provided.
文摘On February 20,2025,China National Petroleum Corporation announced that China's first ultra-deep scientific exploration well-Shenditake 1 Well-successfully reached a depth of 10910 m underground(Fig.1).Deep Earth Towerke 1 Well is located in the heart of the Taklamakan Desert in the Xinjiang Uyghur Autonomous Region,within the territory of Shaya County.It has become the deepest vertical well in Asia and the second deepest in the world.The well has successively set five major engineering records:The deepest global tailpipe cementing,the deepest global cable imaging logging,the fastest global onshore drilling to exceed 10000 m,the deepest direct well drilling in Asia,and the deepest onshore coring in Asia.This marks another major breakthrough for China in the field of“Deep Earth”exploration,following its achievements in“Deep Space”and“Deep Sea.”
基金support from the"Intelligent Recognition Industry Service Center"as part of the Featured Areas Research Center Program under the Higher Education Sprout Project by the Ministry of Education(MOE)in Taiwan,and the National Science and Technology Council,Taiwan,under grants[113-2622-E-224-002]and[113-2221-E-224-041]support was provided by Isuzu Optics Corporation.
文摘Automated classification of retinal fundus images is essential for identifying eye diseases,though there is earlier research on applying deep learning models designed especially for detecting tessellation in retinal fundus images.This study classifies 4 classes of retinal fundus images with 3 diseased fundus images and 1 normal fundus image,by creating a refined VGG16 model to categorize fundus pictures into tessellated,normal,myopia,and choroidal neovascularization groups.The approach utilizes a VGG16 architecture that has been altered with unique fully connected layers and regularization using dropouts,along with data augmentation techniques(rotation,flip,and rescale)on a dataset of 302 photos.Training involves class weighting and critical callbacks(early halting,learning rate reduction,checkpointing)to maximize performance.Gains in accuracy(93.42%training,77.5%validation)and improved class-specific F1 scores are attained.Grad-CAM’s Explainable AI(XAI)highlights areas of the images that are important for each categorization,making it interpretable for better understanding of medical experts.These results highlight the model’s potential as a helpful diagnostic tool in ophthalmology,providing a clear and practical method for the early identification and categorization of retinal disorders,especially in cases such as tessellated fundus images.
基金The Natural Sciences and Engineering Research Council of Canada(NSERC)funded this review study.
文摘This reviewpresents a comprehensive technical analysis of deep learning(DL)methodologies in biomedical signal processing,focusing on architectural innovations,experimental validation,and evaluation frameworks.We systematically evaluate key deep learning architectures including convolutional neural networks(CNNs),recurrent neural networks(RNNs),transformer-based models,and hybrid systems across critical tasks such as arrhythmia classification,seizure detection,and anomaly segmentation.The study dissects preprocessing techniques(e.g.,wavelet denoising,spectral normalization)and feature extraction strategies(time-frequency analysis,attention mechanisms),demonstrating their impact on model accuracy,noise robustness,and computational efficiency.Experimental results underscore the superiority of deep learning over traditional methods,particularly in automated feature extraction,real-time processing,cross-modal generalization,and achieving up to a 15%increase in classification accuracy and enhanced noise resilience across electrocardiogram(ECG),electroencephalogram(EEG),and electromyogram(EMG)signals.Performance is rigorously benchmarked using precision,recall,F1-scores,area under the receiver operating characteristic curve(AUC-ROC),and computational complexitymetrics,providing a unified framework for comparing model efficacy.Thesurvey addresses persistent challenges:synthetic data generationmitigates limited training samples,interpretability tools(e.g.,Gradient-weighted Class Activation Mapping(Grad-CAM),Shapley values)resolve model opacity,and federated learning ensures privacy-compliant deployments.Distinguished from prior reviews,this work offers a structured taxonomy of deep learning architectures,integrates emerging paradigms like transformers and domain-specific attention mechanisms,and evaluates preprocessing pipelines for spectral-temporal trade-offs.It advances the field by bridging technical advancements with clinical needs,such as scalability in real-world settings(e.g.,wearable devices)and regulatory alignment with theHealth Insurance Portability and Accountability Act(HIPAA)and General Data Protection Regulation(GDPR).By synthesizing technical rigor,ethical considerations,and actionable guidelines for model selection,this survey establishes a holistic reference for developing robust,interpretable biomedical artificial intelligence(AI)systems,accelerating their translation into personalized and equitable healthcare solutions.
基金supported by the National Natural Science Foundation of China(No.12104141).
文摘Aiming at the problem that the bit error rate(BER)of asymmetrically clipped optical orthogonal frequency division multiplexing(ACO-OFDM)space optical communication system is significantly affected by different turbulence intensities,the deep learning technique is proposed to the polarization code decoding in ACO-OFDM space optical communication system.Moreover,this system realizes the polarization code decoding and signal demodulation without frequency conduction with superior performance and robustness compared with the performance of traditional decoder.Simulations under different turbulence intensities as well as different mapping orders show that the convolutional neural network(CNN)decoder trained under weak-medium-strong turbulence atmospheric channels achieves a performance improvement of about 10^(2)compared to the conventional decoder at 4-quadrature amplitude modulation(4QAM),and the BERs for both 16QAM and 64QAM are in between those of the conventional decoder.
文摘The deep sea holds vital resources and spatial potential for future human survival and development,reflecting the common interests and concerns of all mankind.Amidst unprecedented global transformations in a hundred years,the deep sea has emerged as a critical area of international competition and serves as a new frontier for resource extraction,a strategic space for military competition,and a contested space for great power rivalry and rule-making.
基金funding support from the National Natural Science Foundation of China(Grant Nos.42277161,42230709).
文摘The warming and thawing of permafrost are the primary factors that impact the stability of embankments in cold regions.However,due to uncertainties in thermal boundaries and soil properties,the stochastic modeling of thermal regimes is challenging and computationally expensive.To address this,we propose a knowledge-integrated deep learning method for predicting the stochastic thermal regime of embankments in permafrost regions.Geotechnical knowledge is embedded in the training data through numerical modeling,while the neural network learns the mapping from the thermal boundary and soil property fields to the temperature field.The effectiveness of our method is verified in comparison with monitoring data and numerical analysis results.Experimental results show that the proposed method achieves good accuracy with small coefficient of variation.It still provides satisfactory accuracy as the coefficient of variation increases.The proposed knowledge-integrated deep learning method provides an efficient approach to predict the stochastic thermal regime of heterogeneous embankments.It can also be used in other permafrost engineering investigations that require stochastic numerical modeling.
基金supported by the National Natural Science Foundation of China(Nos.42107211 and U23A20651)the Natural Science Foundation of Sichuan Province(No.2025ZNSFSC0097)。
文摘Layered rock masses represent complex geological formations commonly encountered in the surrounding rock of deep engineering excavations(Hou et al.,2019;Xu et al.,2017;Yang C H et al.,2009;Xian and Tan,1989).These rock masses are predominantly composed of sedimentary,para-metamorphic,and volcanic rock types,characterized by a set of prominent,primary bedding structural planes(layers)exhibiting relatively consistent orientations and significant spatial continuity.
基金supported by the National Key Research and Development Program of China,Grant No.2020YFB0905900.
文摘The Virtual Power Plant(VPP),as an innovative power management architecture,achieves flexible dispatch and resource optimization of power systems by integrating distributed energy resources.However,due to significant differences in operational costs and flexibility of various types of generation resources,as well as the volatility and uncertainty of renewable energy sources(such as wind and solar power)and the complex variability of load demand,the scheduling optimization of virtual power plants has become a critical issue that needs to be addressed.To solve this,this paper proposes an intelligent scheduling method for virtual power plants based on Deep Reinforcement Learning(DRL),utilizing Deep Q-Networks(DQN)for real-time optimization scheduling of dynamic peaking unit(DPU)and stable baseload unit(SBU)in the virtual power plant.By modeling the scheduling problem as a Markov Decision Process(MDP)and designing an optimization objective function that integrates both performance and cost,the scheduling efficiency and economic performance of the virtual power plant are significantly improved.Simulation results show that,compared with traditional scheduling methods and other deep reinforcement learning algorithms,the proposed method demonstrates significant advantages in key performance indicators:response time is shortened by up to 34%,task success rate is increased by up to 46%,and costs are reduced by approximately 26%.Experimental results verify the efficiency and scalability of the method under complex load environments and the volatility of renewable energy,providing strong technical support for the intelligent scheduling of virtual power plants.
基金supported by the National Key R&D Program of China(2022YFD1401600)the National Science Foundation for Distinguished Young Scholars of Zhejang Province,China(LR23C140001)supported by the Key Area Research and Development Program of Guangdong Province,China(2018B020205003 and 2020B0202090001).
文摘Inferring phylogenetic trees from molecular sequences is a cornerstone of evolutionary biology.Many standard phylogenetic methods(such as maximum-likelihood[ML])rely on explicit models of sequence evolution and thus often suffer from model misspecification or inadequacy.The on-rising deep learning(DL)techniques offer a powerful alternative.Deep learning employs multi-layered artificial neural networks to progressively transform input data into more abstract and complex representations.DL methods can autonomously uncover meaningful patterns from data,thereby bypassing potential biases introduced by predefined features(Franklin,2005;Murphy,2012).Recent efforts have aimed to apply deep neural networks(DNNs)to phylogenetics,with a growing number of applications in tree reconstruction(Suvorov et al.,2020;Zou et al.,2020;Nesterenko et al.,2022;Smith and Hahn,2023;Wang et al.,2023),substitution model selection(Abadi et al.,2020;Burgstaller-Muehlbacher et al.,2023),and diversification rate inference(Voznica et al.,2022;Lajaaiti et al.,2023;Lambert et al.,2023).In phylogenetic tree reconstruction,PhyDL(Zou et al.,2020)and Tree_learning(Suvorov et al.,2020)are two notable DNN-based programs designed to infer unrooted quartet trees directly from alignments of four amino acid(AA)and DNA sequences,respectively.
基金Research on the Entry Point of School-Enterprise Co-construction of Intelligent Manufacturing Majors to Serve the Construction of the Core Area of the“Belt and Road”(Project No.:BJKY-2024-354)。
文摘With the proposal and implementation of the“Belt and Road”initiative,economic development requires the drive of a large number of talents and real industries.Local governments along the route also encourage universities and enterprises to carry out high-level school-enterprise cooperation to promote the effective sharing of education and economy,thus ensuring the development of the regional economy.In order to better adapt to relevant national policies,promote regional economic development,and supply high-quality and skilled talents to society,higher vocational colleges should strengthen education reform,introduce the school-enterprise cooperation mechanism,achieve the deep integration between schools and enterprises,and promote regional economic development.Based on this,this paper analyzes and studies the deep cooperation model between higher vocational colleges and enterprises under the“Belt and Road”initiative for reference.
