检索结果-内蒙古大学图书馆

A method for detecting floating objects on water based on edge computing

学校读者我要写书评

暂无评论

A method for detecting floating objects on water based on ed...

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： He Li Shuaipeng Yang Jinjiang Liu Honglin Fang Zhumu Fu Rui Zhang Huimei Jia Lianmeng Lv Henan Costar Group Co. Ltd Nanyang Henan China College of Information Engineering Henan University of Science and Technology Luoyang Henan China Henan Engineering Research Center of Intelligent Processing for Big Data of Digital Image School of Computer Science and Technology Nanyang Normal University Nanyang China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunication Beijing China Xi'an Hengpin Electronic Technology Co. Ltd Xi’an China

With the development and application of computer vision, many target detection networks are applied to the detection of floating objects in rivers. For the detection problems such as small targets easily missed and misdetected in water surface floating object detection tasks and difficult to deploy models. An edge computing-oriented approach to river floater detection is proposed. First, a four-fold down-sampling feature layer is added to the YOLOv5 network which enhances more target detail features and improves the detection capability of small objects. Second, CA (Coordinate Attention) is added to the Backbone to suppress background noise interference, and different pooling is used to accommodate different hierarchical features. Then, a bilinear interpolation method is adopted for up-sampling to avoid the loss of small object features. Design a data enhancement algorithm for small targets based on Mosaic to increase the number of small objects and enrich the training background. Finally, for the edge computing architecture platform, the channel pruning algorithm is used to prune and compress the model structure to adapt to the computing capability of edge devices. The experimental results show that the method can effectively improve the detection capability of the network for floating objects on the water surface. The detection accuracy can reach 93.6%, and the detection speed can be maintained at 36 frames per second, which can achieve high-precision real-time detection of floating objects on the water surface.

关键词：

Hypercomplex Low Rank Reconstruction for Nmr Spectroscopy with Cloud Computing ⋆

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Guo, Yi Zhan, Jiaying Tu, Zhangren Zhou, Yirong Wu, Jianfan Hong, Qing Orekhov, Vladislav Qu, Xiaobo Guo, Di School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China Department of Electronic Science Biomedical Intelligent Cloud R&D Center Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361005 China China Mobile Group Xiamen361005 China Swedish NMR Center Department of Chemistry and Molecular Biology University of Gothenburg Gothenburg41390 Sweden

Nuclear magnetic resonance (NMR) spectroscopy serves as an important tool to analyze chemicals and proteins in bioengineering. Multi-dimensional NMR offers a major improvement in resolution with multi-dimensional spectrum, but significantly increases data acquisition time and produces hypercomplex data that is difficult to be handled. To reduce this time, non-uniformly sampling can be applied to obtain undersampled data and using a reconstruction approach, such as the state-of-the-art low-rank method, to remove the spectral artifacts introduced by undersampling. However, only complex format of signal, including the real and imaginary parts, is considered in previous low-rank approach, which is less efficient when dealing with hypercomplex data that has multiple components. To deal with this problem, a hypercomplex low-rank model is proposed by introducing an adjoint matrix operation and then solved with a fast matrix factorization algorithm. This method efficiently uses redundant information among all the components of hypercomplex signal. Using simulated data and real protein data, we demonstrate that the proposed method provides a fast and high-fidelity reconstruction of hypercomplex NMR spectroscopy. Furthermore, an open-access and easy-to-use cloud-computing platform is developed for this method. © 2022, The Authors. All rights reserved.

关键词： Nuclear magnetic resonance spectroscopy

An Efficient Multi-Order Cascade Distillation Model for the Detection of Small Targets and Occluded Objects in Transmission Line Inspection

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Qu, Zhaoyang Zang, Jiye Dong, Yunchang Qu, Nan Song, Siqi Jiang, Tao Li, Min Liang, Feng Li, Lingcong School of Computer Northeast Electric Power University Jilin132012 China Jilin Electric Power Big Data Intelligent Processing Engineering Technology Research Center Jilin132012 China State Grid Jilin Electric Power Research Institute Changchun130012 China State Grid Jiangsu Electric Power Co. Ltd. Nanjing Power Supply Company 210000 China Northeast Electric Power Design Institute Co. Ltd. of China Power Engineering Consulting Group Changchun130021 China

The proposed cascade distillation detection model improves the accuracy of small target defect detection and robustness in complex environments during UAV inspection of transmission lines. Firstly, the cascading modules of the shared backbone network are designed: the dynamic anchor box generation module and the bounding box refinement module. The former collects and processes areas where there may be targets, outputs high-quality location information, and distills it to the latter, and the latter is responsible for refining and filtering this part of the information, which solves the problems of missed detection of model targets and lack of a priori information on target locations. A high-order aggregated feature extraction network is introduced to enhance feature extraction of small and obscured targets. Lastly, a spatially deformable attention mechanism optimizes sampling point selection and attention weight calculation by aggregating nearby contextual information, improving bounding box adjustment. © 2023, The Authors. All rights reserved.

关键词： Electric lines

Sinogram upsampling using Primal-Dual UNet for undersampled CT and radial MRI reconstruction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ernst, Philipp Chatterjee, Soumick Rose, Georg Speck, Oliver Nürnberger, Andreas Faculty of Computer Science Otto von Guericke University Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany Otto von Guericke University Research Campus STIMULATE Magdeburg Germany Genomics Research Centre Human Technopole Milan Italy Institute for Medical Engineering Otto von Guericke University Magdeburg Germany German Centre for Neurodegenerative Disease Magdeburg Germany Centre for Behavioural Brain Sciences Magdeburg Germany

Computed tomography (CT) and magnetic resonance imaging (MRI) are two widely used clinical imaging modalities for noninvasive diagnosis. However, both of these modalities come with certain problems. CT uses harmful ionising radiation, and MRI suffers from slow acquisition speed. Both problems can be tackled by undersampling, such as sparse sampling. However, such undersampled data leads to lower resolution and introduces artefacts. Several techniques, including deep learning based methods, have been proposed to reconstruct such data. However, the undersampled reconstruction problem for these two modalities was always considered as two different problems and tackled separately by different research works. This paper proposes a unified solution for both sparse CT and undersampled radial MRI reconstruction, achieved by applying Fourier transform-based pre-processing on the radial MRI and then finally reconstructing both modalities using sinogram upsampling combined with filtered back-projection. The Primal-Dual network is a deep learning based method for reconstructing sparsely-sampled CT data. This paper introduces Primal-Dual UNet, which improves the Primal-Dual network in terms of accuracy and reconstruction speed. The proposed method resulted in an average SSIM of 0.932±0.021 while performing sparse CT reconstruction for fan-beam geometry with a sparsity level of 16, achieving a statistically significant improvement over the previous model, which resulted in 0.919±0.016. Furthermore, the proposed model resulted in 0.903±0.019 and 0.957±0.023 average SSIM while reconstructing undersampled brain and abdominal MRI data with an acceleration factor of 16, respectively-statistically significant improvements over the original model, which resulted in 0.867±0.025 and 0.949±0.025. Finally, this paper shows that the proposed network not only improves the overall image quality, but also improves the image quality for the regions-of-interest: liver, kidneys, and spleen;as well

关键词： Image reconstruction

Author Correction: Large-scale benchmarking of circRNA detection tools reveals large differences in sensitivity but not in precision

学校读者我要写书评

暂无评论

Nature methods 2025年第2期22卷 448页

作者： Marieke Vromman Jasper Anckaert Stefania Bortoluzzi Alessia Buratin Chia-Ying Chen Qinjie Chu Trees-Juen Chuang Roozbeh Dehghannasiri Christoph Dieterich Xin Dong Paul Flicek Enrico Gaffo Wanjun Gu Chunjiang He Steve Hoffmann Osagie Izuogu Michael S Jackson Tobias Jakobi Eric C Lai Justine Nuytens Julia Salzman Mauro Santibanez-Koref Peter Stadler Olivier Thas Eveline Vanden Eynde Kimberly Verniers Guoxia Wen Jakub Westholm Li Yang Chu-Yu Ye Nurten Yigit Guo-Hua Yuan Jinyang Zhang Fangqing Zhao Jo Vandesompele Pieter-Jan Volders OncoRNALab Cancer Research Institute Ghent (CRIG) Department of Biomolecular Medicine Ghent University Ghent Belgium. Department of Molecular Medicine University of Padova Padova Italy. Genomics Research Center Academia Sinica Taipei City Taiwan. Institute of Crop Science and Institute of Bioinformatics Zhejiang University Zhejiang China. Department of Biomedical Data Science and of Biochemistry Stanford University Stanford CA USA. Klaus Tschira Institute for Integrative Computational Cardiology Department of Internal Medicine III University Hospital Heidelberg German Center for Cardiovascular Research (DZHK) Heidelberg Germany. School of Basic Medical Science Department of Medical Genetics Wuhan University Wuhan China. EMBL-EBI Hinxton UK. Collaborative Innovation Center of Jiangsu Province of Cancer Prevention and Treatment of Chinese Medicine School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China. Computational Biology Group Leibniz Institute on Aging - Fritz Lipmann Institute (FLI) Jena Germany. Biosciences Institute Faculty of Medical Sciences Newcastle University Newcastle UK. Translational Cardiovascular Research Center University of Arizona - College of Medicine Phoenix Phoenix AZ USA. Sloan Kettering Institute New York NY USA. Bioinformatics Group Department of Computer Science and Interdisciplinary Center for Bioinformatics Universität Leipzig Leipzig Germany. Data Science Institute I-Biostat Hasselt University Hasselt Belgium. State Key Laboratory of Bioelectronics School of Biological Sciences and Medical Engineering Southeast University Nanjing China. Department of Biochemistry and Biophysics National Bioinformatics Infrastructure Sweden Science for Life Laboratory Stockholm University Stockholm Sweden. Center for Molecular Medicine Children's Hospital Fudan University and Shanghai Key Laboratory of Medical Epigenetics International Laboratory of Medical Epigenetics and Metab

Fast Interpretable Greedy-Tree Sums

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tan, Yan Shuo Singh, Chandan Nasseri, Keyan Agarwal, Abhineet Duncan, James Ronen, Omer Epland, Matthew Kornblith, Aaron Yu, Bin Department of Statistics and Data Science National University of Singapore Singapore Department of Electrical Engineering and Computer Sciences UC Berkeley United States Microsoft Research United States Department of Statistics UC Berkeley United States Graduate Group in Biostatistics UC Berkeley United States Overjet Department of Emergency Medicine UC San Francisco United States Department of Pediatrics UC San Francisco United States

Modern machine learning has achieved impressive prediction performance, but often sacrifices interpretability, a critical consideration in high-stakes domains such as medicine. In such settings, practitioners often use highly interpretable decision tree models, but these suffer from inductive bias against additive structure. To overcome this bias, we propose Fast Interpretable Greedy-Tree Sums (FIGS), which generalizes the CART algorithm to simultaneously grow a flexible number of trees in summation. By combining logical rules with addition, FIGS is able to adapt to additive structure while remaining highly interpretable. Extensive experiments on real-world datasets show that FIGS achieves state-of-the-art prediction performance. To demonstrate the usefulness of FIGS in high-stakes domains, we adapt FIGS to learn clinical decision instruments (CDIs), which are tools for guiding clinical decision-making. Specifically, we introduce a variant of FIGS known as G-FIGS that accounts for the heterogeneity in medical data. G-FIGS derives CDIs that reflect domain knowledge and enjoy improved specificity (by up to 20% over CART) without sacrificing sensitivity or interpretability. To provide further insight into FIGS, we prove that FIGS learns components of additive models, a property we refer to as disentanglement. Further, we show (under oracle conditions) that unconstrained tree-sum models leverage disentanglement to generalize more efficiently than single decision tree models when fitted to additive regression functions. Finally, to avoid overfitting with an unconstrained number of splits, we develop Bagging-FIGS, an ensemble version of FIGS that borrows the variance reduction techniques of random forests. Bagging-FIGS enjoys competitive performance with random forests and XGBoost on real-world datasets. © 2022, CC BY.

关键词： Decision trees

Automated SSIM Regression for Detection and Quantification of Motion Artefacts in Brain MR Images

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sciarra, Alessandro Chatterjee, Soumick Dünnwald, Max Placidi, Giuseppe Nürnberger, Andreas Speck, Oliver Oeltze-Jafra, Steffen The Medicine and Digitalization - MedDigit Group Department of Neurology Medical Faculty University Hospital Magdeburg Germany the Department of Biomedical Magnetic Resonance Faculty of Natural Sciences Otto von Guericke University Germany The Data and Knowledge Engineering Group Faculty of Computer Science Otto von Guericke University Germany The Genomics Research Centre Human Technopole Milan Italy The Faculty of Computer Science Otto von Guericke University Germany The Department of Life Health and Environmental Sciences University of L'Aquila Italy The Center for Behavioral Brain Sciences Magdeburg Germany The German Center for Neurodegenerative Disease Magdeburg Germany

Motion artefacts in magnetic resonance brain images can have a strong impact on diagnostic confidence. The assessment of MR image quality is fundamental before proceeding with the clinical diagnosis. Motion artefacts can alter the delineation of structures such as the brain, lesions or tumours and may require a repeat scan. Otherwise, an inaccurate (e.g. correct pathology but wrong severity) or incorrect diagnosis (e.g. wrong pathology) may occur."Image quality assessment" as a fast, automated step right after scanning can assist in deciding if the acquired images are diagnostically sufficient. An automated image quality assessment based on the structural similarity index (SSIM) regression through a residual neural network is proposed in this work. Additionally, a classification into different groups - by subdividing with SSIM ranges - is evaluated. Importantly, this method predicts SSIM values of an input image in the absence of a reference ground truth image. The networks were able to detect motion artefacts, and the best performance for the regression and classification task has always been achieved with ResNet-18 with contrast augmentation. The mean and standard deviation of residuals' distribution were µ = −0.0009 and σ = 0.0139, respectively. Whilst for the classification task in 3, 5 and 10 classes, the best accuracies were 97, 95 and 89%, respectively. The results show that the proposed method could be a tool for supporting neuro-radiologists and radiographers in evaluating image quality quickly. Copyright © 2022, The Authors. All rights reserved.

关键词： Image quality

Mitigating Translationese in Low-resource Languages: The Storyboard Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kuwanto, Garry Urua, Eno-Abasi Amuok, Priscilla Muhammad, Shamsuddeen Hassan Aremu, Anuoluwapo Otiende, Verrah Nanyanga, Loice Nyoike, Teresiah Akpan, Aniefon Udouboh, Nsima Archibong, Idongesit Moses, Idara Ige, Ifeoluwatayo Ajibade, Benjamin Awokoya, Olumide Abdulmumin, Idris Aliyu, Saminu Mohammad Iro, Ruqayya Ahmad, Ibrahim Said Smith, Deontae Michaels, Praise-EL Adelani, David Ifeoluwa Wijaya, Derry Tanti Andy, Anietie Department of Computer Science Boston University United States University of Uyo Nigeria Imperial College London United Kingdom Rochester Institute of Technology United States Data Science for Social Impact Research Group University of Pretoria South Africa Bayero University Kano Nigeria Institute for Experiential AI Northeastern University United States Department of Electrical Engineering and Computer Science Howard University United States University College London United Kingdom Monash University Indonesia Indonesia Masakhane

Low-resource languages often face challenges in acquiring high-quality language data due to the reliance on translation-based methods, which can introduce the translationese effect. This phenomenon results in translated sentences that lack fluency and naturalness in the target language. In this paper, we propose a novel approach for data collection by leveraging storyboards to elicit more fluent and natural sentences. Our method involves presenting native speakers with visual stimuli in the form of storyboards and collecting their descriptions without direct exposure to the source text. We conducted a comprehensive evaluation comparing our storyboard-based approach with traditional text translation-based methods in terms of accuracy and fluency. Human annotators and quantitative metrics were used to assess translation quality. The results indicate a preference for text translation in terms of accuracy, while our method demonstrates worse accuracy but better fluency in the language focused. © 2024, CC BY.

关键词： Translation (languages)

Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jin, Ming Shi, Guangsi Li, Yuan-Fang Xiong, Bo Zhou, Tian Salim, Flora D. Zhao, Liang Wu, Lingfei Wen, Qingsong Pan, Shirui School of Information and Communication Technology Griffith University Gold Coast Australia Department of Data Science and AI Monash University Melbourne Australia International Max Plank Research School for Intelligent Systems The University of Stuttgart Stuttgart Germany Alibaba Group Hangzhou China School of Computer Science and Engineering University of New South Wales Sydney Australia Department of Computer Science Emory University Atlanta United States Anytime.AI New York United States Squirrel Ai Learning Bellevue United States

Time series forecasting has remained a focal point due to its vital applications in sectors such as energy management and transportation planning. Spectral-temporal graph neural network is a promising abstraction underlying most time series forecasting models that are based on graph neural networks (GNNs). However, more is needed to know about the underpinnings of this branch of methods. In this paper, we establish a theoretical framework that unravels the expressive power of spectral-temporal GNNs. Our results show that linear spectral-temporal GNNs are universal under mild assumptions, and their expressive power is bounded by our extended first-order Weisfeiler-Leman algorithm on discrete-time dynamic graphs. To make our findings useful in practice on valid instantiations, we discuss related constraints in detail and outline a theoretical blueprint for designing spatial and temporal modules in spectral domains. Building on these insights and to demonstrate how powerful spectral-temporal GNNs are based on our framework, we propose a simple instantiation named Temporal Graph Gegenbauer Convolution (TGGC), which significantly outperforms most existing models with only linear components and shows better model efficiency. Our findings pave the way for devising a broader array of provably expressive GNN-based models for time series. © 2023, CC BY.

关键词： Time series