检索结果-内蒙古大学图书馆

Fast light-field 3D microscopy with out-of-distribution detection and adaptation through Conditional Normalizing Flows

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Vizcaíno, Josué Page Symvoulidis, Panagiotis Wang, Zeguan Jelten, Jonas Favaro, Paolo Boyden, Edward S. Lasser, Tobias Computational Imaging and Inverse Problems Department of Informatics School of Computation Information and Technology Technical University of Munich Germany Munich Institute of Biomedical Engineering Technical University of Munich Germany Synthetic Neurobiology Group Massachusetts Institute of Technology United States Computer Vision Group University of Bern Switzerland

Real-time 3D fluorescence microscopy is crucial for the spatiotemporal analysis of live organisms, such as neural activity monitoring. The eXtended field-of-view light field microscope (XLFM), also known as Fourier light field microscope, is a straightforward, single snapshot solution to achieve this. The XLFM acquires spatial-angular information in a single camera exposure. In a subsequent step, a 3D volume can be algorithmically reconstructed, making it exceptionally well-suited for real-time 3D acquisition and potential analysis. Unfortunately, traditional reconstruction methods (like deconvolution) require lengthy processing times (0.0220 Hz), hampering the speed advantages of the XLFM. Neural network architectures can overcome the speed constraints at the expense of lacking certainty metrics, which renders them untrustworthy for the biomedical realm. This work proposes a novel architecture to perform fast 3D reconstructions of live immobilized zebrafish neural activity based on a conditional normalizing flow. It reconstructs volumes at 8 Hz spanning 512x512x96 voxels, and it can be trained in under two hours due to the small dataset requirements (10 image-volume pairs). Furthermore, normalizing flows allow for exact Likelihood computation, enabling distribution monitoring, followed by out-of-distribution detection and retraining of the system when a novel sample is detected. We evaluate the proposed method on a cross-validation approach involving multiple in-distribution samples (genetically identical zebrafish) and various out-of-distribution ones. © 2023, CC BY.

关键词： Neurons

Intelligent Spectrum Occupancy Prediction for Realistic Measurements: GRU based Approach

学校读者我要写书评

暂无评论

Intelligent Spectrum Occupancy Prediction for Realistic Meas...

International Black Sea Conference on Communications and Networking (BlackSeaCom)

作者： Armed Tusha Batuhan Kaplan Hakan Ali Cı rpan Khalid Qaraqe Hü seyin Arslan Department of Electrical and Electronics Engineering Istanbul Medipol University Istanbul Turkey Department of Electrical and Computer Engineering Texas A&#x0026 M University at Qatar Doha Qatar Informatics and Information Security Research Center (B&#x0130 LGEM) T&#x00DC B&#x0130 TAK Kocaeli Turkey Department of Electronics and Communication Engineering Istanbul Technical University Istanbul Turkey Department of Electrical Engineering University of South Florida Tampa Florida USA

ISBN: (数字)9781665497497

ISBN: (纸本)9781665497503

Cognitive radio (CR) technology has always been a research hotspot in the wireless communications field as it has the potential to significantly improve system capacity at the cost of increased processing time and power consumption, which represent highly critical performance indicators (CPI) towards next-generation wireless networks. In particular, the main problem in the CR-based communication links resides in the prediction of spectrum availability in accordance with strict secondary user (SU) CPIs requirements, which is not achievable through the traditional approaches. In this work, we design a novel hierarchical spectrum prediction model, taking advantage from the recurrent neural network (RNN) with the focus on the gated recurrent unit network (GRU). Specifically, the proposed system architecture offers an accrue prediction on the spectrum availability for the SU considering the prior information of the primary user (PU). The performance of the proposed design is illustrated through extensive simulation results. Specifically, real spectrum measurements gathered from Doha, in Qatar are performed to assess the performance accuracy of the designed architecture. In particular different from the conventional scheme that uses a binary representation of spectrum occupancy (idle is “0” and occupied is “1”), we perform training and prediction over the minimum and maximum recorded measurements.

关键词： Training Recurrent neural networks Atmospheric measurements Wireless networks Simulation Urban areas Sea measurements

Robust Recovery of Low Rank Matrix by Nonconvex Rank Regularization 11th

学校读者我要写书评

暂无评论

Robust Recovery of Low Rank Matrix by Nonconvex Rank Regular...

11th International Conference on Image and Graphics, ICIG 2021

作者： Zhang, Hengmin Luo, Wei Du, Wenli Qian, Jianjun Yang, Jian Zhang, Bob Department of Computer and Information Science University of Macau 999078 China School of Information Science and Engineering Key Laboratory of Advanced Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (纸本)9783030873578

As we know, nuclear norm based regularization methods have the real-world applications in pattern recognition and computer vision. However, there exists a biased estimator when nuclear norm relaxes the rank function. To solve this issue, we focus on studying nonconvex rank regularization problems for both robust matrix completion (RMC) and low rank representation (LRR), respectively. By extending both to a general low rank matrix minimization problem, we develop a nonconvex alternating direction method of multipliers (ADMM). Moreover, the convergence results, i.e., the variable sequence generated by the nonconvex ADMM is bounded and its subsequence converges to a stationary point. Meanwhile, its limiting point satisfies the Karush-Kuhn-Tucher (KKT) conditions provided under some milder assumptions. Numerical experiments can verify the convergence properties of the theoretical results and the performance shows its superiority on both image inpainting and subspace clustering. © 2021, Springer Nature Switzerland AG.

关键词： Clustering algorithms

Lightning-Fast Dual-Layer Lossless Coding for Radiance Format High Dynamic Range Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Suzuki, Taizo Yukikata, Sara Yang, Kai Yoshida, Taichi The Institute of Engineering Information and Systems University of Tsukuba Ibaraki305-8573 Japan Sky Co. Ltd. Tokyo108-0075 Japan Da-Jiang Innovations Science and Technology Japan Co. Ltd. Tokyo108-0075 Japan The Department of Computer and Network Engineering Graduate School of Informatics and Engineering The University of Electro-Communications Tokyo182-8585 Japan

This paper proposes a fast dual-layer lossless coding for high dynamic range images (HDRIs) in the Radiance format. The coding, which consists of a base layer and a lossless enhancement layer, provides a standard dynamic range image (SDRI) without requiring an additional algorithm at the decoder and can losslessly decode the HDRI by adding the residual signals (residuals) between the HDRI and SDRI to the SDRI, if desired. To suppress the dynamic range of the residuals in the enhancement layer, the coding directly uses the mantissa and exponent information from the Radiance format. To further reduce the residual energy, each mantissa is modeled (estimated) as a linear function, i.e., a simple linear regression, of the encoded-decoded SDRI in each region with the same exponent. This is called simple linear regressive mantissa estimator. Experimental results show that, compared with existing methods, our coding reduces the average bitrate by approximately 1.57-6.68 % and significantly reduces the average encoder implementation time by approximately 87.13-98.96 %. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

MassSpecGym: A benchmark for the discovery and identification of molecules

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bushuiev, Roman Bushuiev, Anton de Jonge, Niek F. Young, Adamo Kretschmer, Fleming Samusevich, Raman Heirman, Janne Wang, Fei Zhang, Luke Dührkop, Kai Ludwig, Marcus Haupt, Nils A. Kalia, Apurva Brungs, Corinna Schmid, Robin Greiner, Russell Wang, Bo Wishart, David S. Liu, Li-Ping Rousu, Juho Bittremieux, Wout Rost, Hannes Mak, Tytus D. Hassoun, Soha Huber, Florian van der Hooft, Justin J.J. Stravs, Michael A. Böcker, Sebastian Sivic, Josef Pluskal, Tomáš Institute of Organic Chemistry and Biochemistry The Czech Academy of Sciences Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Republic Bioinformatics Group Wageningen University & Research Netherlands Department of Computer Science University of Toronto Canada Institute for Computer Science Friedrich Schiller University Jena Germany Department of Computer Science University of Antwerp Belgium Department of Computing Science University of Alberta Canada Alberta Machine Intelligence Institute Canada Department of Molecular Genetics University of Toronto Canada Bright Giant GmbH Germany Department of Computer Science Tufts University United States Department of Biological Sciences University of Alberta Canada Department of Computer Science Aalto University Finland Mass Spectrometry Data Center National Institute of Standards and Technology United States Department of Chemical and Biological Engineering Tufts University United States Centre for Digitalisation and Digitality University of Applied Sciences Düsseldorf Germany Department of Biochemistry University of Johannesburg South Africa Eawag: Swiss Federal Institute of Aquatic Science and Technology Switzerland

The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym – the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at https://***/pluskal-lab/MassSpecGym. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

OCU-Net: A Novel U-Net Architecture for Enhanced Oral Cancer Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Albishri, Ahmed Shah, Syed Jawad Lee, Yugyung Wang, Rong Computer Science School of Science and Engineering University of Missouri-Kansas City Kansas City United States College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Department of Oral and Craniofacial Sciences School of Dentistry University of Missouri - Kansas City Kansas City United States

Accurate detection of oral cancer is crucial for improving patient outcomes. However, the field faces two key challenges: the scarcity of deep learning-based image segmentation research specifically targeting oral cancer and the lack of annotated data. Our study proposes OCU-Net, a pioneering U-Net image segmentation architecture exclusively designed to detect oral cancer in hematoxylin and eosin (H&E) stained image datasets. OCU-Net incorporates advanced deep learning modules, such as the Channel and Spatial Attention Fusion (CSAF) module, a novel and innovative feature that emphasizes important channel and spatial areas in H&E images while exploring contextual information. In addition, OCU-Net integrates other innovative components such as Squeeze-and-Excite (SE) attention module, Atrous Spatial Pyramid Pooling (ASPP) module, residual blocks, and multi-scale fusion. The incorporation of these modules showed superior performance for oral cancer segmentation for two datasets used in this research. Furthermore, we effectively utilized the efficient ImageNet pre-trained MobileNet-V2 model as a backbone of our OCU-Net to create OCU-Netm, an enhanced version achieving state-of-the-art results. Comprehensive evaluation demonstrates that OCU-Net and OCU-Netm outperformed existing segmentation methods, highlighting their precision in identifying cancer cells in H&E images from OCDC and ORCA datasets. © 2023, CC BY.

关键词： Image segmentation

AlGaAs soliton microcombs at room temperature

学校读者我要写书评

暂无评论

AlGaAs soliton microcombs at room temperature

Conference on Lasers and Electro-Optics (CLEO)

作者： Lue Wu Weiqiang Xie Chao Xiang Lin Chang Yan Yu Hao-Jing Chen Yoshihisa Yamamoto John E. Bowers Kerry J. Vahala Myoung-Gyun Suh T. J. Watson Laboratory of Applied Physics California Institute of Technology Pasadena CA USA Department of Electrical and Computer Engineering University of California Santa Barbara Santa Barbara CA USA Physics & Informatics Laboratories NTT Research Inc. Sunnyvale CA USA

Soliton generation in AlGaAs microresonators at room temperation is reported for the first time. The destabilizing thermo-optic effect is shown to instead provide stability for high soliton repetition rates. The optic... 详细信息

ISBN: (纸本)9781957171258

关键词： Dielectric microcavities Frequency combs Microresonators Mode locking Q factor Thermo optic effects

Going the Extra Mile in Face Image Quality Assessment: A Novel Database and Model

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Su, Shaolin Lin, Hanhe Hosu, Vlad Wiedemann, Oliver Sun, Jinqiu Zhu, Yu Liu, Hantao Zhang, Yanning Saupe, Dietmar School of Computer Science and Engineering Northwestern Polytechnical University China School of Science and Engineering University of Dundee DundeeDD1 4HN United Kingdom Department of Computer and Information Science University of Konstanz Konstanz78464 Germany School of Computer Science and Informatics Cardiff University CardiffCF24 4AG United Kingdom

An accurate computational model for image quality assessment (IQA) benefits many vision applications, such as image filtering, image processing, and image generation. Although the study of face images is an important subfield in computer vision research, the lack of face IQA data and models limits the precision of current IQA metrics on face image processing tasks such as face superresolution, face enhancement, and face editing. To narrow this gap, in this paper, we first introduce the largest annotated IQA database developed to date, which contains 20,000 human faces - an order of magnitude larger than all existing rated datasets of faces - of diverse individuals in highly varied circumstances. Based on the database, we further propose a novel deep learning model to accurately predict face image quality, which, for the first time, explores the use of generative priors for IQA. By taking advantage of rich statistics encoded in well pretrained off-the-shelf generative models, we obtain generative prior information and use it as latent references to facilitate blind IQA. The experimental results demonstrate both the value of the proposed dataset for face IQA and the superior performance of the proposed model. © 2022, CC BY.

关键词： Database systems

FedMonitor: An Implementation Architecture for Monitoring of Resources and Events'Notifications on Federated Cloud Computing Infrastructures

学校读者我要写书评

暂无评论

FedMonitor: An Implementation Architecture for Monitoring of...

International Conference on Emerging Trends in Networks and computer Communications (ETNCC)

作者： Emmanuel Adetiba Uche Nnaji John S. Wejin Festus Ojesanmi Matthew B. Akanle Priscilla O. Ajayi Faith O. Sweetwiliams Surendra C. Thakur Ezekiel F. Adebiyi Department of Electrical and Information Engineering and Covenant Applied Informatics & Communication African Center of Excellene(CApIC-ACE) Covenant University Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban South Africa Department of Computer and Information Science & CApIC-ACE Covenant University Ota Nigeria Department of Electrical and Information Engineering & CApIC-ACE Covenant University Jalingo Nigeria Department of Computer Science Tareba State University Jalingo Nigeria Covenant Applied Informatics & Communication African Center of Excellene(CApIC-ACE) Covenant University Ota Nigeria Department of Electrical and Information Engineering Covenant University & CApIC-ACE Covenant University Ota Nigeria Center for Systems and Information Services & CApIC-ACE Covenant University Ota Nigeria Department of Information Technology and KZN e-Skills Co-Laboratory Durban University of Technology Durban South Africa Covenant University Bioinformatics Research (CUBRe) Covenant University Ota Ogun State Nigeria African Center of Excellence in Bioinformatics & Data Intensive Science Makerere University Kampala Uganda

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

In the evolving landscape of cloud computing, federated cloud infrastructures present unique challenges and opportunities for resource and application monitoring. Monitoring the diverse array of cloud resources and applications within a federated cloud environment is crucial for delivering consistent Quality of Service (QoS) and continuous oversight across various cloud applications and infrastructure. Despite the various successes documented in the literature on multi-cloud monitoring, existing frameworks have not fully explored or provided enough insights into centralized monitoring of resources, applications, and network devices in a federated cloud environment. This paper introduces FedMonitor, an implementation architecture designed to enhance the monitoring and notification capabilities in federated cloud environments by building on the theoretical ideals in our earlier work (i.e. FEDARGOS-V1). FedMonitor leverages Prometheus and Grafana to crawl, manage and visualize metrics from diverse software services, hardware resources, and network devices within a federated cloud environment. The results demonstrate hat FedMonitor improves the effectiveness of resource and application monitoring in federated cloud environments.

关键词： Measurement Cloud computing Visualization computer architecture Quality of service Production Software Real-time systems Stakeholders Monitoring