检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Fu, Kexue Gao, Peng Liu, Shaolei Wang, Manning Digital Medical Research Center School of Basic Medical Science Fudan University China Shandong Computer Science Center China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China Shanghai AILab China

Recently, the pre-training paradigm combining Transformer and masked language modeling in BERT has achieved tremendous success not only in NLP, but also in images and point clouds. However, directly extending BERT from NLP to point clouds requires first training a discrete Variational AutoEncoder (dVAE) as the tokenizer, which results in a complex two-stage process, as in Point-BERT. Inspired by BERT and MoCo, we propose POS-BERT, a one-stage BERT pre-training method for point clouds. Specifically, we use the masked patch modeling (MPM) task to perform point cloud pre-training, which aims to recover masked patch information under the supervision of a tokenizer's output. Unlike Point-BERT, whose tokenizer is extra-trained and frozen, we propose a momentum tokenizer which is dynamically updated during training the Transformer. Furthermore, in order to better learn high-level semantic representation, we integrate contrastive learning into the proposed framework to maximize the class token consistency between augmented point cloud pairs. Experiments show that POS-BERT achieves the state-of-the-art performance on linear SVM classification of ModelNet40 with fixed feature extractors, and it exceeds Point-BERT by 3.5%. In addition, POS-BERT has significantly improved many downstream tasks, including fine-tuned classification, few-shot classification and part segmentation. The code and the trained model will be released soon. © 2023, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Federated Semi-supervised Learning for Medical Image Segmentation with Intra-client and Inter-client Consistency

Federated Semi-supervised Learning for Medical Image Segment...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yubin Zheng Peng Tang Tianjie Ju Hao Wang Weidong Qiu Jagath C. Rajapakse School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China College of Basic Medical Sciences Shanghai Jiao Tong University Shanghai China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Medical image segmentation plays a vital role in medical image analysis. However, it is impractical to build a large-scale centralized segmentation dataset due to the privacy of medical images. Federated learning (FL) aims to train a shared model of isolated clients without local data exchange which aligns well with the scarcity and privacy characteristics of medical images. Moreover, there is a large amount of unlabeled data in clients due to the difficulty in annotating medical images. Federated semi-supervised learning (FSSL) can leverage the unlabeled data of clients to improve the performance of the global model. Many existing FSSL methods apply the complicated semi-supervised learning protocols and some of them neglect the problem of data heterogeneity in FL. In this paper, we propose a novel federated semi-supervised learning framework for medical image segmentation incorporating intra-client and inter-client consistency learning. The intra-client consistency learning can introduce global data noise in data augmentation which can improve the generalization ability of the model and reduce the impact of data heterogeneity. The inter-client consistency learning is proposed to expand the feature search space and learn the ensemble knowledge of different clients. The two consistency learning mechanisms are achieved with the assistance of a Variational Autoencoder (VAE) trained collaboratively by clients. The experimental results illustrate that our method outperforms the state-of-the-art methods under different FSSL settings. The code is available at https://***/zyb98/FV2IC.

关键词： Image segmentation Data privacy Protocols Biological system modeling Noise Semisupervised learning Feature extraction Data models Robustness Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Yang, Zhiwei Meng, Yucong Fu, Kexue Wang, Shuo Song, Zhijian Academy for Engineering & Technology Fudan University Shanghai200433 China Digital Medical Research Center School of Basic Medical Science Fudan University China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China Shandong Computer Science Center China

Weakly supervised semantic segmentation (WSSS) with image-level labels intends to achieve dense tasks without laborious annotations. However, due to the ambiguous contexts and fuzzy regions, the performance of WSSS, especially the stages of generating Class Activation Maps (CAMs) and refining pseudo masks, widely suffers from ambiguity while being barely noticed by previous literature. In this work, we propose UniA, a unified single-staged WSSS framework, to efficiently tackle this issue from the perspective of uncertainty inference and affinity diversification, respectively. When activating class objects, we argue that the false activation stems from the bias to the ambiguous regions during the feature extraction. Therefore, we design a more robust feature representation with a probabilistic Gaussian distribution and introduce the uncertainty estimation to avoid the bias. A distribution loss is particularly proposed to supervise the process, which effectively captures the ambiguity and models the complex dependencies among features. When refining pseudo labels, we observe that the affinity from the prevailing refinement methods intends to be similar among ambiguities. To this end, an affinity diversification module is proposed to promote diversity among semantics. A mutual complementing refinement is proposed to initially rectify the ambiguous affinity with multiple inferred pseudo labels. More importantly, a contrastive affinity loss is further designed to diversify the relations among unrelated semantics, which reliably propagates the diversity into the whole feature representations and helps generate better pseudo masks. Extensive experiments are conducted on PASCAL VOC, MS COCO, and medical ACDC datasets, which validate the efficiency of UniA tackling ambiguity and the superiority over recent single-staged or even most multi-staged competitors. Codes will be publicly available here. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Automation Intervention for Monitoring Agriculture Farming Scale: A Review 14

Automation Intervention for Monitoring Agriculture Farming S...

引用

14th International Conference on computing Communication and Networking Technologies, ICCCNT 2023

作者： Joshi, Kapil Kumar, Santosh Bhatla, Shruti Kaushik, Vishal Anandaram, Harishchander Kumar, Anil Uttaranchal University Department of Cse Uttaranchal Institute of Technology Dehradun India Sharda University Department of Mathematics Sharda School of Basic Sciences and Research UP Greater Noida India Graphic Era Hill University Department of Computer Science and Engineering Uttarakhand Dehradun India Upes School of Computer Science Dehradun India Amrita Vishwa Vidyapeetham Centre for Computational Engineering and Networking Tamil Nadu Coimbatore India Dit University School of Computing Dehradun India

ISBN: (纸本)9798350335095

Agricultural data is only valuable when it has been managed successfully. As data has evolved into the fundamental ingredient in contemporary agriculture to assist farmers with vital decision, latest developments in managing data are causing Smart Agriculture to rise dramatically. With factual information obtained by sensors, significant advantages emerge with the goal of enhancing production and ecology. This type of data-driven farm management is built on information that can boost efficiency by preventing resource waste and contamination of the ecosystem. Data-driven farming, with the assistance of automated solutions using artificial intelligence techniques, lays the groundwork for potential sustainable *** article analyses the current state of sophisticated agricultural systems by rehashing each critical step, from data processing in field crops to variable interest rate implementations, so that farmers can make optimised decision making to save funds while safeguarding the natural environment and converting how meal would be generated to meet the upcoming population explosion. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Impact of the magnetothermoelectric effect on the diffusion of conserved charges in hot and dense hadronic matter

引用

Physical Review D 2024年第3期110卷 034023-034023页

作者： He-Xia Zhang Ke-Ming Shen Yu-Xin Xiao Ben-Wei Zhang Key Laboratory of Atomic and Subatomic Structure and Quantum Control (MOE) Guangdong Basic Research Center of Excellence for Structure and Fundamental Interactions of Matter Institute of Quantum Matter Guangdong-Hong Kong Joint Laboratory of Quantum Matter Guangdong Provincial Key Laboratory of Nuclear Science Southern Nuclear Science Computing Center School of Science Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics

We investigate the thermoelectric effect, which describes the generation of an electric field induced by temperature and conserved charge chemical potential gradients, in the hot and dense hadronic matter created in heavy-ion collisions. Utilizing the Boltzmann kinetic theory within the repulsive mean-field hadron resonance gas model, we evaluate both the diffusion thermopower matrix and diffusion coefficient matrix for the baryon number (B), electric charge (Q), and strangeness (S). The Landau-Lifshitz choice for the rest frame of the fluid is enforced in the derivation. We find that the thermoelectric effect hinders the diffusion processes of multiple conserved charges, particularly reducing the coupling between electric charge and baryon number (strangeness) in baryon (strangeness) diffusion. Given that the repulsive mean-field interactions between hadrons have a significant effect on the diffusion thermopower matrix and diffusion coefficient matrix in the baryon-rich region, we extend the investigation to include the impact of magnetic fields, analyzing the magneto-thermoelectric effect on both the diffusion coefficient matrix and the Hall-like diffusion coefficient matrix. The sensitivities of the magnetic field-dependent diffusion thermopower matrix and magneto-thermoelectric modified diffusion coefficient matrix to the choices of various transverse conditions are also studied.

关键词： Big bang nucleosynthesis Nuclear many-body theory Nuclear matter Nuclear physics of explosive environments Quantum chromodynamics Thermal & statistical models Transport in heavy-ion collisions

来源：评论

学校读者我要写书评

暂无评论

Two-Body Hadronic Weak Decays of Bottomed Hadrons

引用

Chinese Physics Letters 2024年第2期41卷 26-35页

作者：张颖何广朝叶全兴严大程华俊王倩 Key Laboratory of Atomic and Subatomic Structure and Quantum Control(MOE) Guangdong Basic Research Center of Excellence for Structure and Fundamental Interactions of MatterInstitute of Quantum MatterSouth China Normal UniversityGuangzhou 510006China Guangdong-Hong Kong Joint Laboratory of Quantum Matter Guangdong Provincial Key Laboratory of Nuclear ScienceSouthern Nuclear Science Computing CenterSouth China Normal UniversityGuangzhou 510006China School of Mathematics and Physics Changzhou UniversityChangzhou 213164China Southern Center for Nuclear-Science Theory(SCNT) Institute of Modern PhysicsChinese Academy of SciencesHuizhou 516000China

The structure of light diquarks plays a crucial role in formation of exotic hadrons beyond the conventional quark model, especially with regard to the line shapes of bottomed hadron decays. We study the two-body hadronic weak decays of bottomed baryons and bottomed mesons to probe the light diquark structure and to pin down the quark–quark correlations in the diquark picture. It is found that the light diquark does not favor a compact structure. For instance, the isoscalar diquark [ud] in Λ_(b)^(0) can be easily split and rearranged to form ■via the color-suppressed transition. This provides a hint that the hidden charm pentaquark states produced in Λ_(b)^(0) decays could be the ■chadronic molecular candidates. This quantitative study resolves the apparent conflicts between the production mechanism and the molecular nature of these P_(c) states observed in experiment.

关键词： transition structure quark

来源：评论

学校读者我要写书评

暂无评论

Mass spectra of strange double charm pentaquarks with strangeness S=−1

引用

Physical Review D 2024年第5期110卷 056022页

作者： Zi-Yan Yang Qian Wang Wei Chen Key Laboratory of Atomic and Subatomic Structure and Quantum Control (MOE) Guangdong Basic Research Center of Excellence for Structure and Fundamental Interactions of Matter Institute of Quantum Matter Guangdong-Hong Kong Joint Laboratory of Quantum Matter Guangdong Provincial Key Laboratory of Nuclear Science Southern Nuclear Science Computing Center Southern Center for Nuclear-Science Theory (SCNT) Institute of Modern Physics School of Physics

The observation of the Tcs¯(2900) indicates the potential existence of strange double charm pentaquarks based on the heavy antidiquark symmetry. We systematically study the mass spectra of strange double charm pentaquarks with strangeness S=−1 in both molecular and compact structures for quantum numbers JP=1/2−, 3/2−, 5/2−. By constructing the interpolating currents, the mass spectra can be extracted from the two-point correlation functions in the framework of QCD sum rule method. In the molecular picture, we find that the Ξc′+D*+, Ξc*+D*+, Ξcc*++K¯*0, and Ωcc*+ρ+ may form molecular strange double charm pentaquarks. In both pictures, the masses of the JP=1/2−,3/2− pentaquarks locate within the 4.2–4.6 GeV and 4.2–4.5 GeV regions, respectively. As all of them are above the thresholds of their strong decay channels, they behave as a broad state, making them challenging to be detected experimentally. On the other hand, the strange double charm pentaquark with JP=5/2− lies below its strong decay channel, which may be a very narrow state and easy to identify experimentally. The best observed channel is its semileptonic decay to double charm baryon. As the result, we strongly suggest experiments to search for JP=5/2− strange double charm pentaquarks first.

关键词： Multiquark bound states Nonperturbative effects in field theory Quantum chromodynamics Strong interaction

来源：评论

学校读者我要写书评

暂无评论

-Hilfer fractional Langevin differential equation having multipoint boundary conditions

引用

Boundary Value Problems 2024年第1期2024卷 1-25页

作者： Cheng, HuiYan Naila Zada, Akbar Popa, Ioan-Lucian Kallekh, Afef Department of Basic Education Zhengzhou Technology and Business University Zhengzhou China Department of Mathematics University of Peshawar Peshawar Pakistan Department of Computing Mathematics and Electronics “1 Decembrie 1918” University of Alba Iulia Alba Iulia Romania Faculty of Mathematics and Computer Science Transilvania University of Brasov Brasov Romania Department of Mathematics Faculty of Science King Khalid University Abha Saudi Arabia

The primary objective of this manuscript is to investigate the existence and uniqueness of solutions for the Langevin $(\mathtt{k},\varphi )$ -Hilfer fractional differential equation of different orders with multipoint nonlocal fractional integral boundary conditions. We consider the generalized version of the Hilfer fractional diferential equation called as $(\mathtt{k},\varphi )$ -Hilfer fractional differential equation. We provide some significant outcomes about $(\mathtt{k},\varphi )$ -Hilfer fractional Langevin differential equation that requires deriving equivalent fractional integral equation to $(\mathtt{k},\varphi )$ -Hilfer Langevin fractional differential equation. The existence result is established using the Krasnoselskii’s fixed-point theorem, while the uniqueness is addressed with the help of Banach contraction principle. Additionally, we investigate the different forms of Ulam stability for the solution of the mentioned problem, under specific conditions. To validate our main outcomes, we present a detailed example at the end of the manuscript.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation

arXiv

引用

arXiv 2023年

作者： Li, Shiman Wang, Haoran Meng, Yucong Zhang, Chenxi Song, Zhijian Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment planning. Thus, it is of great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly and witnessed remarkable progress in multi-organ segmentation. However, obtaining an appropriately sized and fine-grained annotated dataset of multiple organs is extremely hard and expensive. Such scarce annotation limits the development of high-performance multi-organ segmentation models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer learning leveraging external datasets, semi-supervised learning using unannotated datasets and partially-supervised learning integrating partially-labeled datasets have led the dominant way to break such dilemma in multi-organ segmentation. We first review the traditional fully supervised method, then present a comprehensive and systematic elaboration of the 3 abovementioned learning paradigms in the context of multi-organ segmentation from both technical and methodological perspectives, and finally summarize their challenges and future trends. Copyright © 2023, The Authors. All rights reserved.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Spatial Heterogeneity Modeling Using Machine Learning Based on a Hybrid of Random Forest and Convolutional Neural Network (CNN)

引用

Journal of Data Analysis and Information Processing 2024年第3期12卷 319-347页

作者： Amadou Kindy Barry Anthony Waititu Gichuhi Lawrence Nderu Department of Mathematics Pan African University Institute for Basic Sciences Technology and Innovation (PAUISTI) Nairobi Kenya Department of Statistics and Actuarial Science Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya Department of Computing School and Information Technology (SCIT) Jomo Kenyatta University of Agriculture and Technology (JKUAT) Nairobi Kenya

Spatial heterogeneity refers to the variation or differences in characteristics or features across different locations or areas in space. Spatial data refers to information that explicitly or indirectly belongs to a particular geographic region or location, also known as geo-spatial data or geographic information. Focusing on spatial heterogeneity, we present a hybrid machine learning model combining two competitive algorithms: the Random Forest Regressor and CNN. The model is fine-tuned using cross validation for hyper-parameter adjustment and performance evaluation, ensuring robustness and generalization. Our approach integrates Global Moran’s I for examining global autocorrelation, and local Moran’s I for assessing local spatial autocorrelation in the residuals. To validate our approach, we implemented the hybrid model on a real-world dataset and compared its performance with that of the traditional machine learning models. Results indicate superior performance with an R-squared of 0.90, outperforming RF 0.84 and CNN 0.74. This study contributed to a detailed understanding of spatial variations in data considering the geographical information (Longitude & Latitude) present in the dataset. Our results, also assessed using the Root Mean Squared Error (RMSE), indicated that the hybrid yielded lower errors, showing a deviation of 53.65% from the RF model and 63.24% from the CNN model. Additionally, the global Moran’s I index was observed to be 0.10. This study underscores that the hybrid was able to predict correctly the house prices both in clusters and in dispersed areas.

关键词： Spatial Heterogeneity Spatial Data Feature Selection Standardization Machine Learning Models Hybrid Models

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：