Arthropod melanization is a crucial defense mechanism mediated by a complex cascade of CLIP domain serine proteases(CLIPs).In this study,it was confirmed that microRNA-11903a(miR-11903a)targets Aedes-CLIPB9(AeCLIPB9)b...Arthropod melanization is a crucial defense mechanism mediated by a complex cascade of CLIP domain serine proteases(CLIPs).In this study,it was confirmed that microRNA-11903a(miR-11903a)targets Aedes-CLIPB9(AeCLIPB9)by bioinformatics prediction and dual-luciferase reporter assays.Following intrathoracic injection of miR-11903a agomir and antagomir,Real-time quantitative polymerase chain reaction confirmed that AeCLIPB9 is negatively regulated by miR-11903a.Spatiotemporal expression analysis revealed that miR-11903a is most abundant in 4th instar larvae,followed by pupae and adults,and highly expressed in the wings,head,and midgut of female adults.Following pathogen infection,AeCLIPB9 and miR-11903a exhibited opposite expression trends,indicating their potential roles in mosquito innate immunity.To further investigate the relationship between AeCLIPB9 and miR-11903a,double-strand CLIPB9 was synthesized and RNA interference was performed.Seven-d survival assays revealed that both AeCLIPB9 and miR-11903a were crucial immune factors in fighting pathogens.Finally,longevity assays demonstrated that miR-11903a influenced mosquito lifespan.展开更多
To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervis...To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.展开更多
Accurate temperature control and effective oxide removal are essential for achieving high-quality epitaxial growth in molecular beam epitaxy(MBE).However,traditional methods often rely on manual identification of refl...Accurate temperature control and effective oxide removal are essential for achieving high-quality epitaxial growth in molecular beam epitaxy(MBE).However,traditional methods often rely on manual identification of reflection high-energy electron diffraction(RHEED)patterns.This process is heavily influenced by the grower’s experience,leading to issues with reproducibility and limiting the potential for automation.In this report,we propose an unsupervised learning framework for realtime RHEED analysis during the deoxidation process.By incorporating temporal similarity constraints into contrastive learning,our model generates smooth and interpretable feature trajectories that illustrate transitions in the deoxidation state,thus eliminating the need for manual labeling.The model,pre-trained using grouped contrastive loss,shows significant improvement in RHEED feature boundary discrimination and localization of critical regions.We evaluated its generalizability through two transfer learning strategies:calibration-free clustering and few-shot fine-tuning.The pre-trained model achieved a clustering accuracy of 88.1%for GaAs deoxidation samples without additional labels and reached an accuracy of 94.3%to 95.5%after fine-tuning with just five sample pairs across GaAs,Ge,and InAs substrates.This framework is optimized for resource-constrained edge devices,allowing for real-time,plug-and-play integration with existing MBE systems and swift adaptation across various materials and equipment.This work paves the way for greater automation and improved reproducibility in semiconductor manufacturing.展开更多
Lacustrine groundwater discharge(LGD)plays an important role in water resources management.Previous studies have focused on LGD process in a single lake,but the differences in LGD process within the same region have n...Lacustrine groundwater discharge(LGD)plays an important role in water resources management.Previous studies have focused on LGD process in a single lake,but the differences in LGD process within the same region have not been thoroughly investigated.In this study,multiple tracers(hydrochemistry,𝛿D,𝛿18O and 222Rn)were used to compare mechanisms of LGD in Daihai and Ulansuhai Lake in Inner Mongoli1,Northwest China.The hydrochemical types showed a trend from groundwater to lake water,indicating a hydraulic connection between them.In addition,the𝛿D and𝛿18O values of sediment pore water were between the groundwater and lake water,indicating the LGD processes.The radon mass balance model was used to estimate the average groundwater discharge rates of Daihai and Ulansuhai Lake,which were 2.79 mm/day and 3.02 mm/day,respectively.The total nitrogen(TN),total phosphorus(TP),and fluoride inputs associated with LGD in Daihai Lake accounted for 97.52%,96.59%,and 95.84%of the total inputs,respectively.In contrast,TN,TP and fluoride inputs in Ulansuhai Lake were 53.56%,40.98%,and 36.25%,respectively.This indicates that the pollutant inputs associated with LGD posed a potential threat to the ecological stability of Daihai and Ulansuhai Lake.By comparison,the differences of LGD process and associated pollutant flux were controlled by hydrogeological conditions,lakebed permeability and human activities.This study provides a reference for water resources management in Daihai and Ulansuhai Lake basins while improving the understanding of LGD in the Yellow River basin.展开更多
Deep graph contrastive clustering has attracted widespread attentions due to its self-supervised representation learning paradigm and superior clustering performance.Although,two challenges emerge and result in high c...Deep graph contrastive clustering has attracted widespread attentions due to its self-supervised representation learning paradigm and superior clustering performance.Although,two challenges emerge and result in high computational costs.Most existing contrastive methods adopt the data augmentation and then representation learning strategy,where representation learning with trainable graph convolution is coupled with complex and fixed data augmentation,inevitably limiting the efficiency and flexibility.The similarity metric between positive-negative sample pairs is complex and contrastive objective is partial,limiting the discriminability of representation learning.To solve these challenges,a novel wide graph clustering network(WGCN)adhering to representation and then augmentation framework is proposed,which mainly consists of multiorder filter fusion(MFF)and double-level contrastive learning(DCL)modules.Specifically,the MFF module integrates multiorder low-pass filters to extract smooth and multi-scale topological features,utilizing self-attention fusion to reduce redundancy and obtain comprehensive embedding representation.Further,the DCL module constructs two augmented views by the parallel parameter-unshared Siamese encoders rather than complex augmentations on graph.To achieve simple yet effective self-supervised learning,representation self-supervision and structural consistency oriented double-level contrastive loss is designed,where representation self-supervision maximizes the agreement between pairwise augmented embedding representations and structural consistency promotes the mutual information correlation between appending neighborhoods with similar semantics.Extensive experiments on six benchmark datasets demonstrate the superiority of the proposed WGCN,especially highlighting its time-saving characteristic.The code could be available in the https://github.com/Tianxiang Zhao0474/WGCN.展开更多
基金supported by the Major Science and Technology Plan of Hainan Province(ZDKJ2021035)the National Natural Science Foundation of China(U22A20363)the Innovative Research Projects for Postgraduates in Hainan Province(Qhyb2022-41).
文摘Arthropod melanization is a crucial defense mechanism mediated by a complex cascade of CLIP domain serine proteases(CLIPs).In this study,it was confirmed that microRNA-11903a(miR-11903a)targets Aedes-CLIPB9(AeCLIPB9)by bioinformatics prediction and dual-luciferase reporter assays.Following intrathoracic injection of miR-11903a agomir and antagomir,Real-time quantitative polymerase chain reaction confirmed that AeCLIPB9 is negatively regulated by miR-11903a.Spatiotemporal expression analysis revealed that miR-11903a is most abundant in 4th instar larvae,followed by pupae and adults,and highly expressed in the wings,head,and midgut of female adults.Following pathogen infection,AeCLIPB9 and miR-11903a exhibited opposite expression trends,indicating their potential roles in mosquito innate immunity.To further investigate the relationship between AeCLIPB9 and miR-11903a,double-strand CLIPB9 was synthesized and RNA interference was performed.Seven-d survival assays revealed that both AeCLIPB9 and miR-11903a were crucial immune factors in fighting pathogens.Finally,longevity assays demonstrated that miR-11903a influenced mosquito lifespan.
基金supported by the National Natural Science Foundation of China Funded Project(Project Name:Research on Robust Adaptive Allocation Mechanism of Human Machine Co-Driving System Based on NMS Features,Project Approval Number:52172381).
文摘To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.
基金supported by the Beijing Natural Science Foundation(Grant Nos.F251036 and L248103)CAS Project for Young Scientists in Basic Research(Grant Nos.YSBR-090 and YSBR-05)National Natural Science Foundation of China(Grant No.62274159).
文摘Accurate temperature control and effective oxide removal are essential for achieving high-quality epitaxial growth in molecular beam epitaxy(MBE).However,traditional methods often rely on manual identification of reflection high-energy electron diffraction(RHEED)patterns.This process is heavily influenced by the grower’s experience,leading to issues with reproducibility and limiting the potential for automation.In this report,we propose an unsupervised learning framework for realtime RHEED analysis during the deoxidation process.By incorporating temporal similarity constraints into contrastive learning,our model generates smooth and interpretable feature trajectories that illustrate transitions in the deoxidation state,thus eliminating the need for manual labeling.The model,pre-trained using grouped contrastive loss,shows significant improvement in RHEED feature boundary discrimination and localization of critical regions.We evaluated its generalizability through two transfer learning strategies:calibration-free clustering and few-shot fine-tuning.The pre-trained model achieved a clustering accuracy of 88.1%for GaAs deoxidation samples without additional labels and reached an accuracy of 94.3%to 95.5%after fine-tuning with just five sample pairs across GaAs,Ge,and InAs substrates.This framework is optimized for resource-constrained edge devices,allowing for real-time,plug-and-play integration with existing MBE systems and swift adaptation across various materials and equipment.This work paves the way for greater automation and improved reproducibility in semiconductor manufacturing.
基金supported by the Natural Science Foundation of Inner Mongolia Autonomous Region of China(No.2023QN04011)the National Natural Science Foundation of China(Nos.42307092 and 52279067)+1 种基金Ordos Science and Technology Major Project(No.ZD20232303)Project of Key Laboratory of River and Lake in Inner Mongolia Autonomous Region(No.2022QZBZ0003).
文摘Lacustrine groundwater discharge(LGD)plays an important role in water resources management.Previous studies have focused on LGD process in a single lake,but the differences in LGD process within the same region have not been thoroughly investigated.In this study,multiple tracers(hydrochemistry,𝛿D,𝛿18O and 222Rn)were used to compare mechanisms of LGD in Daihai and Ulansuhai Lake in Inner Mongoli1,Northwest China.The hydrochemical types showed a trend from groundwater to lake water,indicating a hydraulic connection between them.In addition,the𝛿D and𝛿18O values of sediment pore water were between the groundwater and lake water,indicating the LGD processes.The radon mass balance model was used to estimate the average groundwater discharge rates of Daihai and Ulansuhai Lake,which were 2.79 mm/day and 3.02 mm/day,respectively.The total nitrogen(TN),total phosphorus(TP),and fluoride inputs associated with LGD in Daihai Lake accounted for 97.52%,96.59%,and 95.84%of the total inputs,respectively.In contrast,TN,TP and fluoride inputs in Ulansuhai Lake were 53.56%,40.98%,and 36.25%,respectively.This indicates that the pollutant inputs associated with LGD posed a potential threat to the ecological stability of Daihai and Ulansuhai Lake.By comparison,the differences of LGD process and associated pollutant flux were controlled by hydrogeological conditions,lakebed permeability and human activities.This study provides a reference for water resources management in Daihai and Ulansuhai Lake basins while improving the understanding of LGD in the Yellow River basin.
基金supported by the National Natural Science Foundation of China(62225303,62403043,62433004)the Beijing Natural Science Foundation(4244085)+1 种基金the Postdoctoral Fellowship Program of China Postdoctoral Science Foundation(GZC20230203)the China Postdoctoral Science Foundation(2023M740201)。
文摘Deep graph contrastive clustering has attracted widespread attentions due to its self-supervised representation learning paradigm and superior clustering performance.Although,two challenges emerge and result in high computational costs.Most existing contrastive methods adopt the data augmentation and then representation learning strategy,where representation learning with trainable graph convolution is coupled with complex and fixed data augmentation,inevitably limiting the efficiency and flexibility.The similarity metric between positive-negative sample pairs is complex and contrastive objective is partial,limiting the discriminability of representation learning.To solve these challenges,a novel wide graph clustering network(WGCN)adhering to representation and then augmentation framework is proposed,which mainly consists of multiorder filter fusion(MFF)and double-level contrastive learning(DCL)modules.Specifically,the MFF module integrates multiorder low-pass filters to extract smooth and multi-scale topological features,utilizing self-attention fusion to reduce redundancy and obtain comprehensive embedding representation.Further,the DCL module constructs two augmented views by the parallel parameter-unshared Siamese encoders rather than complex augmentations on graph.To achieve simple yet effective self-supervised learning,representation self-supervision and structural consistency oriented double-level contrastive loss is designed,where representation self-supervision maximizes the agreement between pairwise augmented embedding representations and structural consistency promotes the mutual information correlation between appending neighborhoods with similar semantics.Extensive experiments on six benchmark datasets demonstrate the superiority of the proposed WGCN,especially highlighting its time-saving characteristic.The code could be available in the https://github.com/Tianxiang Zhao0474/WGCN.
