Deep learning techniques are revolutionizing the developmentof medical image segmentation.With the advancement of Transformer models,especially ViT and Swin-Transformer,which enhances the remote-dependent modeling cap...Deep learning techniques are revolutionizing the developmentof medical image segmentation.With the advancement of Transformer models,especially ViT and Swin-Transformer,which enhances the remote-dependent modeling capability of the model through the self-attention mechanism,better segmentation performance can be achieve.Moreover,the high computational cost of Transformer has motivated researchers to explore more efficient models,such as the Mamba model based on state-space modeling(SSM),and for the field of medical segmentation,reducing the number of model parameters is also necessary.In this study,a novel asymmetric model called LA-UMamba was proposed,which integrates visual Mamba module to efficiently capture complex visual features and remote dependencies.The classical design of U-Net was adopted in the upsampling phase to help reduce the number of references and recover more details.To mitigate the information loss problem,an auxiliary U-Net downsampling layer was designed to focus on sizing without extracting features,thus enhancing the protection of input information while maintaining the efficiency of the model.The experiments were conducted on the ACDC MRI cardiac segmentation dataset,and the results showed that the proposed LA-UMamba achieves proved performance compared to the baseline model in several evaluation metrics,such as IoU,Accuracy,Precision,HD and ASD,which improved that the model is successful in optimizing the detail processing and reducing the complexity of the model,providing a new perspective for further optimization of medical image segmentation techniques.展开更多
Purpose Fly scans are indispensable in many experiments at the High Energy Photon Source(HEPS).PandABox,the main platform to implement fly scans at HEPS,needs to be integrated into Mamba,the experiment control system ...Purpose Fly scans are indispensable in many experiments at the High Energy Photon Source(HEPS).PandABox,the main platform to implement fly scans at HEPS,needs to be integrated into Mamba,the experiment control system developed at HEPS based on Bluesky.Methods In less than 600 lines of easily customisable and extensible backend code,provided are full control of PandABox’s TCP server in native ophyd,automated configuration(also including wiring)of“PandA blocks”for constant-speed mapping experiments of various dimensions,as well as generation of scans deliberately fragmented to deal with hardware limits in numbers of exposure frames or sequencer table entries.Results The upper-level control system for PandABox has been ported to Bluesky,enabling the combination of both components’flexibility in fly-scan applications.Based on this backend,a user-friendly Mamba frontend is developed for X-ray fluorescence(XRF)mapping experiments,which provides fully online visual feedback.展开更多
Railway turnouts often develop defects such as chipping,cracks,and wear during use.If not detected and addressed promptly,these defects can pose significant risks to train operation safety and passenger security.Despi...Railway turnouts often develop defects such as chipping,cracks,and wear during use.If not detected and addressed promptly,these defects can pose significant risks to train operation safety and passenger security.Despite advances in defect detection technologies,research specifically targeting railway turnout defects remains limited.To address this gap,we collected images from railway inspectors and constructed a dataset of railway turnout defects in complex environments.To enhance detection accuracy,we propose an improved YOLOv8 model named YOLO-VSS-SOUP-Inner-CIoU(YOLO-VSI).The model employs a state-space model(SSM)to enhance the C2f module in the YOLOv8 backbone,proposed the C2f-VSS module to better capture long-range dependencies and contextual features,thus improving feature extraction in complex environments.In the network’s neck layer,we integrate SPDConv and Omni-Kernel Network(OKM)modules to improve the original PAFPN(Path Aggregation Feature Pyramid Network)structure,and proposed the Small Object Upgrade Pyramid(SOUP)structure to enhance small object detection capabilities.Additionally,the Inner-CIoU loss function with a scale factor is applied to further enhance the model’s detection capabilities.Compared to the baseline model,YOLO-VSI demonstrates a 3.5%improvement in average precision on our railway turnout dataset,showcasing increased accuracy and robustness.Experiments on the public NEU-DET dataset reveal a 2.3%increase in average precision over the baseline,indicating that YOLO-VSI has good generalization capabilities.展开更多
Large language models like Generative Pretrained Transformer (GPT) have significantly advanced natural language processing (NLP) in recent times. They have excelled in tasks such as language translation question answe...Large language models like Generative Pretrained Transformer (GPT) have significantly advanced natural language processing (NLP) in recent times. They have excelled in tasks such as language translation question answering and text generation. However, their effectiveness is limited by the quadratic training complexity of Transformer models O (L2), which makes it challenging to handle complex tasks like classifying long documents. To overcome this challenge researchers have explored architectures and techniques such as sparse attention mechanisms, hierarchical processing and efficient attention modules. A recent innovation called Mamba based on a state space model approach offers inference speed and scalability in sequence length due to its unique selection mechanism. By incorporating this selection mechanism Mamba allows for context reasoning and targeted focus on particular inputs thereby reducing computational costs and enhancing performance. Despite its advantages, the application of Mamba in long document classification has not been thoroughly investigated. This study aims to fill this gap by developing a Mamba-based model, for long document classification and assessing its efficacy across four datasets;Hyperpartisan, 20 Newsgroups, EURLEX and CMU Book Summary. Our study reveals that the Mamba model surpasses NLP models such as BERT and Longformer showcasing exceptional performance and highlighting Mamba’s efficiency in handling lengthy document classification tasks. These results hold implications for NLP applications empowering advanced language models to address challenging tasks with extended sequences and enhanced effectiveness. This study opens doors for the exploration of Mamba’s abilities and its potential utilization, across diverse NLP domains.展开更多
The Late Cretaceous Mamba granodiorite belongs to a part of the Mesozoic Gangdese continental magmatic belt. No quantitative mineralogical study has been made hitherto, and hence the depth at which it formed is poorly...The Late Cretaceous Mamba granodiorite belongs to a part of the Mesozoic Gangdese continental magmatic belt. No quantitative mineralogical study has been made hitherto, and hence the depth at which it formed is poorly constrained. Here we present mineralogical data for the Mamba pluton, including host rocks and their mafic microgranular enclaves（MMEs）, to provide insights into their overall crystallization conditions and information about magma mixing. All amphiboles in the Mamba pluton are calcic, with ~B（Ca＋Na）〉1.5, and Si=6.81-7.42 apfu for the host rocks and Si=6.77-7.35 apfu for the MMEs. The paramount cation substitutions in amphibole include edenite type and tschermakite type. Biotites both in the host rocks and the MMEs collectively have high Mg O（13.19 wt.%-13.03 wt.%） contents, but define a narrow range of Al apfu（atoms per formula unit） variations（2.44-2.57）. The oxygen fugacity estimates are based on the biotite compositions cluster around the NNO buffer. The calculated pressure ranges from 1.2 to 2.1 kbar according to the aluminum-in-hornblende barometer. The computed pressure varies from 0.9 to 1.3 kbar based on the aluminum-in-biotite barometer which corresponds to an average depth of ca. 3.9 km. Besides, the estimates of crystallization pressures vary from 0.8 to 1.4 kbar based on the amphibole barometer proposed by Ridolfi et al.（2010）, which can be equivalent to the depths ranging from 3.1 to 5.2 km. The MMEs have plagioclase oscillatory zonings and quartz aggregates, probably indicating the presence of magma mixing. Besides, core-to-rim element variations（Rb, Sr, Ba, and P） for the K-feldspar megacrysts serve as robust evidence to support magma mixing and crystal fractionation. This indicates the significance of the magma mixing that contributes to the formation of K-feldspar megacryst zonings in the Mamba pluton.展开更多
文摘Deep learning techniques are revolutionizing the developmentof medical image segmentation.With the advancement of Transformer models,especially ViT and Swin-Transformer,which enhances the remote-dependent modeling capability of the model through the self-attention mechanism,better segmentation performance can be achieve.Moreover,the high computational cost of Transformer has motivated researchers to explore more efficient models,such as the Mamba model based on state-space modeling(SSM),and for the field of medical segmentation,reducing the number of model parameters is also necessary.In this study,a novel asymmetric model called LA-UMamba was proposed,which integrates visual Mamba module to efficiently capture complex visual features and remote dependencies.The classical design of U-Net was adopted in the upsampling phase to help reduce the number of references and recover more details.To mitigate the information loss problem,an auxiliary U-Net downsampling layer was designed to focus on sizing without extracting features,thus enhancing the protection of input information while maintaining the efficiency of the model.The experiments were conducted on the ACDC MRI cardiac segmentation dataset,and the results showed that the proposed LA-UMamba achieves proved performance compared to the baseline model in several evaluation metrics,such as IoU,Accuracy,Precision,HD and ASD,which improved that the model is successful in optimizing the detail processing and reducing the complexity of the model,providing a new perspective for further optimization of medical image segmentation techniques.
基金supported by the National Science Foundation for Young Scientists of China(Grants No.12005253 and No.12205328)the Strategic Priority Research Program of Chinese Academy of Sciences(XDB37000000)the Technological Innovation Program of Institute of High Energy Physics of Chinese Academy of Sciences(E25455U210).
文摘Purpose Fly scans are indispensable in many experiments at the High Energy Photon Source(HEPS).PandABox,the main platform to implement fly scans at HEPS,needs to be integrated into Mamba,the experiment control system developed at HEPS based on Bluesky.Methods In less than 600 lines of easily customisable and extensible backend code,provided are full control of PandABox’s TCP server in native ophyd,automated configuration(also including wiring)of“PandA blocks”for constant-speed mapping experiments of various dimensions,as well as generation of scans deliberately fragmented to deal with hardware limits in numbers of exposure frames or sequencer table entries.Results The upper-level control system for PandABox has been ported to Bluesky,enabling the combination of both components’flexibility in fly-scan applications.Based on this backend,a user-friendly Mamba frontend is developed for X-ray fluorescence(XRF)mapping experiments,which provides fully online visual feedback.
文摘Railway turnouts often develop defects such as chipping,cracks,and wear during use.If not detected and addressed promptly,these defects can pose significant risks to train operation safety and passenger security.Despite advances in defect detection technologies,research specifically targeting railway turnout defects remains limited.To address this gap,we collected images from railway inspectors and constructed a dataset of railway turnout defects in complex environments.To enhance detection accuracy,we propose an improved YOLOv8 model named YOLO-VSS-SOUP-Inner-CIoU(YOLO-VSI).The model employs a state-space model(SSM)to enhance the C2f module in the YOLOv8 backbone,proposed the C2f-VSS module to better capture long-range dependencies and contextual features,thus improving feature extraction in complex environments.In the network’s neck layer,we integrate SPDConv and Omni-Kernel Network(OKM)modules to improve the original PAFPN(Path Aggregation Feature Pyramid Network)structure,and proposed the Small Object Upgrade Pyramid(SOUP)structure to enhance small object detection capabilities.Additionally,the Inner-CIoU loss function with a scale factor is applied to further enhance the model’s detection capabilities.Compared to the baseline model,YOLO-VSI demonstrates a 3.5%improvement in average precision on our railway turnout dataset,showcasing increased accuracy and robustness.Experiments on the public NEU-DET dataset reveal a 2.3%increase in average precision over the baseline,indicating that YOLO-VSI has good generalization capabilities.
文摘Large language models like Generative Pretrained Transformer (GPT) have significantly advanced natural language processing (NLP) in recent times. They have excelled in tasks such as language translation question answering and text generation. However, their effectiveness is limited by the quadratic training complexity of Transformer models O (L2), which makes it challenging to handle complex tasks like classifying long documents. To overcome this challenge researchers have explored architectures and techniques such as sparse attention mechanisms, hierarchical processing and efficient attention modules. A recent innovation called Mamba based on a state space model approach offers inference speed and scalability in sequence length due to its unique selection mechanism. By incorporating this selection mechanism Mamba allows for context reasoning and targeted focus on particular inputs thereby reducing computational costs and enhancing performance. Despite its advantages, the application of Mamba in long document classification has not been thoroughly investigated. This study aims to fill this gap by developing a Mamba-based model, for long document classification and assessing its efficacy across four datasets;Hyperpartisan, 20 Newsgroups, EURLEX and CMU Book Summary. Our study reveals that the Mamba model surpasses NLP models such as BERT and Longformer showcasing exceptional performance and highlighting Mamba’s efficiency in handling lengthy document classification tasks. These results hold implications for NLP applications empowering advanced language models to address challenging tasks with extended sequences and enhanced effectiveness. This study opens doors for the exploration of Mamba’s abilities and its potential utilization, across diverse NLP domains.
基金funded by the National Natural Science Foundation of China (Nos. 41403028, 40830317)the China Postdoctoral Science Foundation (No. 2015T80113)+1 种基金China University of Geosciences (No. GMPR201509)the Fundamental Research Funds for the Central Universities of China (No. 2652015018)
文摘The Late Cretaceous Mamba granodiorite belongs to a part of the Mesozoic Gangdese continental magmatic belt. No quantitative mineralogical study has been made hitherto, and hence the depth at which it formed is poorly constrained. Here we present mineralogical data for the Mamba pluton, including host rocks and their mafic microgranular enclaves（MMEs）, to provide insights into their overall crystallization conditions and information about magma mixing. All amphiboles in the Mamba pluton are calcic, with ~B（Ca＋Na）〉1.5, and Si=6.81-7.42 apfu for the host rocks and Si=6.77-7.35 apfu for the MMEs. The paramount cation substitutions in amphibole include edenite type and tschermakite type. Biotites both in the host rocks and the MMEs collectively have high Mg O（13.19 wt.%-13.03 wt.%） contents, but define a narrow range of Al apfu（atoms per formula unit） variations（2.44-2.57）. The oxygen fugacity estimates are based on the biotite compositions cluster around the NNO buffer. The calculated pressure ranges from 1.2 to 2.1 kbar according to the aluminum-in-hornblende barometer. The computed pressure varies from 0.9 to 1.3 kbar based on the aluminum-in-biotite barometer which corresponds to an average depth of ca. 3.9 km. Besides, the estimates of crystallization pressures vary from 0.8 to 1.4 kbar based on the amphibole barometer proposed by Ridolfi et al.（2010）, which can be equivalent to the depths ranging from 3.1 to 5.2 km. The MMEs have plagioclase oscillatory zonings and quartz aggregates, probably indicating the presence of magma mixing. Besides, core-to-rim element variations（Rb, Sr, Ba, and P） for the K-feldspar megacrysts serve as robust evidence to support magma mixing and crystal fractionation. This indicates the significance of the magma mixing that contributes to the formation of K-feldspar megacryst zonings in the Mamba pluton.
