检索结果-内蒙古大学图书馆

Contrastive Learning Driven Self-Supervised Framework for Segmentation of Biomarker of Diabetic Macular Edema

Contrastive Learning Driven Self-Supervised Framework for Se...

IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications

作者： Hina Raja Taimur Hassan Bilal Hassan Naoufel Werghi Hira Raja Siamak Yousefi Department of Ophthalmology University of Tennessee Health Science Center Memphis USA Department of Electrical and Computer Engineering Abu Dhabi University Abu Dhabi United Arab Emirates KUCARS and C2PS Khalifa University Abu Dhabi United Arab Emirates Margalla Institute of Health Sciences Rawalpindi Pakistan

Optical coherence tomography (OCT) has been widely used to investigate the pathological changes due to Diabetic Macular Edema (DME). In this paper, we developed a two-stage self-supervised learning approach to extract DME biomarkers. The backbone of the proposed scheme is the RAG-Net model trained in the first stage to extract different DME biomarkers, such as intra-retinal fluid, sub-retinal fluid, and hard exudates, using the low-shot supervision from the Zhang dataset. In the second training stage, it learns to extract the same biomarkers across the Duke-II dataset in a self-supervised manner (i.e., without using any ground-truth annotations) via the triplet loss function. We validated the proposed approach across both datasets at the inference stage, where it achieved the mean $\mathbf{IoU}$ score of 0.7610, and 0.7232, outperforming the state-of-the-art by 1.734%, and 4.839% for extracting DME biomarkers irrespective of the scanner specifications, and vendor artifacts across the Zhang and Duke-II datasets, respectively. In addition, we employed an external BIOMISA dataset to evaluate the proposed model and obtained an IOU of 0.752. The suggested model has the potential to improve clinical practice by allowing more objective assessment of DME patients. In the future, we plan to expand the application of our self-supervised model to other ocular diseases, such as glaucoma and AMD, and to incorporate more imaging modalities, such as fundus photographs and OCT-Angiography (OCTA).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heuristic Modularity Maximization Algorithms for Community Detection Rarely Return an Optimal Partition or Anything Similar

arXiv

引用

arXiv 2023年

作者： Aref, Samin Mostajabdaveh, Mahdi Chheda, Hriday Department of Mechanical and Industrial Engineering University of Toronto M5S3G8 Canada Huawei Technologies Canada V5C 6S7 Canada Department of Computer Science University of Toronto M5S2E4 Canada

Community detection is a fundamental problem in computational sciences with extensive applications in various fields. The most commonly used methods are the algorithms designed to maximize modularity over different partitions of the network nodes. Using 80 real and random networks from a wide range of contexts, we investigate the extent to which current heuristic modularity maximization algorithms succeed in returning maximum-modularity (optimal) partitions. We evaluate (1) the ratio of the algorithms’ output modularity to the maximum modularity for each input graph, and (2) the maximum similarity between their output partition and any optimal partition of that graph. We compare eight existing heuristic algorithms against an exact integer programming method that globally maximizes modularity. The average modularity-based heuristic algorithm returns optimal partitions for only 19.4% of the 80 graphs considered. Additionally, results on adjusted mutual information reveal substantial dissimilarity between the sub-optimal partitions and any optimal partition of the networks in our experiments. More importantly, our results show that near-optimal partitions are often disproportionately dissimilar to any optimal partition. Taken together, our analysis points to a crucial limitation of commonly used modularity-based heuristics for discovering communities: they rarely produce an optimal partition or a partition resembling an optimal partition. If modularity is to be used for detecting communities, exact or approximate optimization algorithms are recommendable for a more methodologically sound usage of modularity within its applicability *** Codes 90C90, 90C10, 90C57, 90C59, 90C35, 05C15, 65K05 Copyright © 2023, The Authors. All rights reserved.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

New boosting approaches for improving cluster-based undersampling in problems with imbalanced data

引用

Decision Analytics Journal 2023年 8卷

作者： Abdullah-All-Tanvir Khandokar, Iftakhar Ali Shatabda, Swakkhar Department of Computer Science and Engineering United International University Plot-2 United City Madani Avenue Badda Dhaka 1212 Bangladesh Center for Artificial Intelligence and Robotics (CAIR) United International University Plot-2 United City Madani Avenue Badda Dhaka 1212 Bangladesh

Class unbalanced datasets are frequently encountered in a variety of areas including health, security, and finance. Often these datasets create bias in the supervised learning models trained for the prediction task. One of the most successful techniques to handle imbalanced data is undersampling. Experiments demonstrate that cluster-based undersampling improves over random undersampling in many cases. In this paper, we propose three new boosting approaches to improve the performance of cluster-based undersampling technique: (i) inject unlabeled data into training data for improved clustering;(ii) keep the instances close to cluster boundary and centroid while undersampling and (iii) remove the majority samples in the neighborhood of minority data in each cluster. We experimented with our boosting methods over 49 standard benchmark datasets and analyzed the performances in terms of standard evaluation metrics. Experimental results suggest these boosting techniques are promising and significantly improve over cluster-based undersampling strategies. © 2023 The Author(s)

关键词： Clustering Data analytics Data imbalance Supervised learning Undersampling

来源：评论

学校读者我要写书评

暂无评论

Combining vibrational and fluorescence microscopies with mass spectrometry imaging for visualization of drug delivery 9

Combining vibrational and fluorescence microscopies with mas...

引用

Visualizing and Quantifying Drug Distribution in Tissue IX 2025

作者： Belsey, Natalie A. Tsikritsis, DImitrios Dondi, Camilla Vorng, Jean-Luc Dexter, Alex Shaw, Michael National Physical Laboratory Hampton Road TeddingtonTW11 0LW United Kingdom School of Chemistry & Chemical Engineering University of Surrey GuildfordGU2 7XH United Kingdom Department of Computer Science University College London LondonWC1E 6BT United Kingdom

ISBN: (纸本)9781510683785

Recent advances in label-free chemical imaging approaches have yielded new methods for measuring drug distribution in biological tissues. Techniques include vibrational spectroscopies in addition to a range of powerful mass spectrometry imaging methods. These techniques offer complementary information, with different strengths and limitations. By combining datasets from several of these techniques using image registration, powerful visualization of cells and tissues can be achieved, enabling high chemical specificity and sensitivity with sub-micron spatial resolution. Here we present several correlative imaging examples that combine vibrational spectroscopic with mass spectrometric imaging, in addition to single and multiphoton fluorescence. This multimodal approach offers optimal visualization of biological structure, in addition to the measured drug distribution. © 2025 SPIE.

关键词： Fluorescence microscopy

来源：评论

学校读者我要写书评

暂无评论

B-scan-sectioned dynamic micro-optical coherence tomography for bulk-motion suppression

引用

Chinese Optics Letters 2022年第2期20卷 34-39页

作者： Chaoliang Chen Weisong Shi Zhiyuan Qiu Victor X.D.Yang Wanrong Gao Advanced Photonics Center School of Electronic Science&EngineeringSoutheast UniversityNanjing 210096China Department of Optical Engineering Nanjing University of Science and TechnologyNanjing 210094China Department of Electrical Computerand Biomedical EngineeringRyerson UniversityTorontoOntario M5B 2K3Canada Division of Neurosurgery Sunnybrook Health Sciences CentreTorontoOntario M4N 3M5Canada Division of Neurosurgery Faculty of MedicineUniversity of TorontoTorontoOntario M5T 1P5Canada

In this Letter, we present B-scan-sectioned dynamic micro-optical coherence tomography(BD-MOCT) for high-quality subcellular dynamic contrast imaging. Dynamic micro-optical coherence tomography(D-MOCT) is a functional optical coherence tomography(OCT) technique performed on high-resolution(micron level) OCT systems;hundreds of consecutive B-scans need to be acquired for dynamic signal extraction, which requires relatively long data acquisition time. Bulk motions occurring during data acquisition(even at the micron level) may degrade the quality of the obtained dynamic contrast images. In BD-MOCT, each full B-scan is divided into several sub-B-scans, and each sub-B-scan repeats multiple times before the sample beam moves to the next sub-B-scan. After all of the sub-B-scans for a full B-scan are completely acquired, we stitch all of the sub-B-scans into the same number of full B-scans. In this way, the time interval between two consecutive stitched B-scans could be reduced multiple times for bulk-motion suppression. The performed scanning protocol modulates the scanning sequences of fast scanning and repeat scanning for improving the dynamic contrast image quality, while the total data acquisition time remains almost the same.

关键词： optical coherence tomography high-resolution imaging dynamic imaging bulk-motion suppression

来源：评论

学校读者我要写书评

暂无评论

Hilbert-Space Ergodicity in Driven Quantum Systems: Obstructions and Designs

arXiv

引用

arXiv 2024年

作者： Pilatowsky-Cameo, Saúl Marvian, Iman Choi, Soonwon Ho, Wen Wei Center for Theoretical Physics Massachusetts Institute of Technology CambridgeMA02139 United States Departments of Physics & Electrical and Computer Engineering Duke University DurhamNC27708 United States Department of Physics National University of Singapore 117551 Singapore Centre for Quantum Technologies National University of Singapore 3 Science Drive 2 117543 Singapore

Despite its long history, a canonical formulation of quantum ergodicity that applies to general classes of quantum dynamics, including driven systems, has not been fully established. Here we introduce and study a notion of quantum ergodicity for closed systems with time-dependent Hamiltonians, defined as statistical randomness exhibited in their longtime dynamics. Concretely, we consider the temporal ensemble of quantum states (time-evolution operators) generated by the evolution, and investigate the conditions necessary for them to be statistically indistinguishable from uniformly random states (operators) in the Hilbert space (space of unitaries). We find that the number of driving frequencies underlying the Hamiltonian needs to be sufficiently large for this to occur. Conversely, we show that statistical pseudo-randomness — indistinguishability up to some large but finite moment, can already be achieved by a quantum system driven with a single frequency, i.e., a Floquet system, as long as the driving period is sufficiently long. Our work relates the complexity of a time-dependent Hamiltonian and that of the resulting quantum dynamics, and offers a fresh perspective to the established topics of quantum ergodicity and chaos from the lens of quantum information. Copyright © 2024, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Development of Unmanned Cargo VTOL Aircraft 1

引用

59th Symposium on engineering Modelling in Mechanics, 2020

作者： Czyba, Roman Gorol, Zbigniew Lemanowicz, Marcin Pawlak, Mariusz Sikora, Adam Faculty of Automatic Control Electronics and Computer Science Department of Automatic Control and Robotics Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland Faculty of Mechanical Engineering Department of Theoretical and Applied Mechanics Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland Faculty of Chemistry Department of Chemical Engineering and Process Design Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland

ISBN: (数字)9783030684556

ISBN: (纸本)9783030684549

The aim of the paper is to present a design cycle regarding to the construction of an unmanned cargo aircraft with own weight up to 25 kg, operating range of up to 100 km and AGL operating ceiling of up to 1 km. The task of the project team was to plan the design cycle, perform analytical calculations and CFD simulations, and finally to build an unmanned aircraft capable of lifting cargo. At the same time, a number of assumptions and technical regulations regarding constructions had to be met, which are specified in legal regulations regarding the given class of unmanned aerial vehicles. In order to achieve optimal UAV aerodynamic properties, including maximization of the payload while minimizing the own weight, aerodynamic calculations and CFD simulations were performed. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Head2Head++: Deep Facial Attributes Re-Targeting

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

引用

IEEE Transactions on Biometrics, Behavior, and Identity science 2021年第1期3卷 31-43页

作者： Doukas, Michail Christos Koujan, Mohammad Rami Sharmanska, Viktoriia Roussos, Anastasios Zafeiriou, Stefanos Department of Computing Imperial College London LondonN1C 4AG United Kingdom College of Engineering Mathematics and Physical Sciences University of Exeter ExeterEX4 4PY United Kingdom Department of Computing Imperial College London LondonSW7 2BU United Kingdom Institute of Computer Science Heraklion700 13 Greece

Facial video re-targeting is a challenging problem aiming to modify the facial attributes of a target subject in a seamless manner by a driving monocular sequence. We leverage the 3D geometry of faces and Generative Adversarial Networks (GANs) to design a novel deep learning architecture for the task of facial and head reenactment. Our method is different to purely 3D model-based approaches, or recent image-based methods that use Deep Convolutional Neural Networks (DCNNs) to generate individual frames. We manage to capture the complex non-rigid facial motion from the driving monocular performances and synthesise temporally consistent videos, with the aid of a sequential Generator and an ad-hoc Dynamics Discriminator network. We conduct a comprehensive set of quantitative and qualitative tests and demonstrate experimentally that our proposed method can successfully transfer facial expressions, head pose and eye gaze from a source video to a target subject, in a photo-realistic and faithful fashion, better than other state-of-the-art methods. Most importantly, our system performs end-to-end reenactment in nearly real-time speed (18 fps). © 2019 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Image color consistency in datasets: the Smooth-TPS3D method

arXiv

引用

arXiv 2024年

作者： Benito-Altamirano, Ismael Martínez-Carpena, David Lizarzaburu-Aguilar, Hanna Ventura, Carles Fàbrega, Cristian Prades, Joan Daniel MIND/IN2UB Department of Electronic and Biomedical Engineering Universitat de Barcelona Carrer de Martí i Franquès 1 Barcelona Barcelona08028 Spain Department of Mathematics and Computer Science Universitat de Barcelona Gran Via de les Corts Catalanes 585 Barcelona Barcelona08007 Spain eHealth Center Faculty of Computer Science Multimedia and Telecommunications Universitat Oberta de Catalunya Rambla del Poblenou 156 Barcelona Barcelona08018 Spain Technische Universität Braunschweig Hans-Sommer Str. 66 BraunschweigD-38106 Germany

Image color consistency is the key problem in digital imaging consistency when creating datasets. Here, we propose an improved 3D Thin-Plate Splines (TPS3D) color correction method to be used, in conjunction with color charts (i.e. Macbeth ColorChecker) or other machine-readable patterns, to achieve image consistency by post-processing. Also, we benchmark our method against its former implementation and the alternative methods reported to date with an augmented dataset based on the Gehler’s ColorChecker dataset. Benchmark includes how corrected images resemble the ground-truth images and how fast these implementations are. Results demonstrate that the TPS3D is the best candidate to achieve image consistency. Furthermore, our Smooth-TPS3D method shows equivalent results compared to the original method and reduced the 11-15% of ill-conditioned scenarios which the previous method failed to less than 1%. Moreover, we demonstrate that the Smooth-TPS method is 20% faster than the original method. Finally, we discuss how different methods offer different compromises between quality, correction accuracy and computational load. © 2024, CC BY-SA.

关键词： Color image processing

来源：评论

学校读者我要写书评

暂无评论

LabPET II scanner performances improvement: Thermal stability control based on FPGA

引用

e-Prime - Advances in Electrical engineering, Electronics and Energy 2023年 6卷

作者： Oukaira, Aziz Said, Dhaou Zbitou, Jamal Fontaine, Réjean Lakhssassi, Ahmed Department of Engineering and Computer Science University of Quebec in Outaouais Gatineau J9A 1L8 QC Canada Department of Electrical and Computer Engineering Sherbrook University Sherbrooke J1K 2R1 QC Canada LABTIC ENSA of Tangier University of Abdelmalek Essaadi Tangier 93000 Morocco ENSA of Tétouan University of Abdelmalek Essaadi Tétouan 93000 Morocco

The LabPET II detection module serves as the fundamental component within Positron Emission Tomography (PET) scanners designed for achieving ultra-high-resolution imaging of small to medium-sized animals as well as the human brain. To ensure peak performance, it is imperative that this module operates consistently at a stable temperature. In this paper, we present an automatic and real-time method to improve the thermal control of the scanner LabPET II by evacuating the heat to reduce the overall temperature and maintain the thermal stability of the system. Based on the Thermo-Electric Cooler (TEC) process, our method applies two numerical techniques, Computational Fluid Dynamics (CFD) and Heat Transfer Analysis (HTA). The Dirichlet Boundary Conditions (DBC) method is applied for the Application-Specific Integrated Circuit (ASIC) at 25^∘ C. The real measurements confirm and validate the simulation results with the Finite Element Method (FEM) based on the software COMSOL Multiphysics™. Field-Programmable Gate Array (FPGA) implementation on the Development and Education (DE1) board is performed with comparative results study. The proposed method is both simple and practical, and ensures thermal stability at 35^∘C for the duration of operation of the scanner, which has a complex structure. © 2023 The Author(s)

关键词： Application-specific integrated circuit Computational fluid dynamics (CFD) Field-programmable gate array (FPGA) Finite element method (FEM) Positron emission tomography (PET) Thermo-electric cooler (TEC)

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：