检索结果-内蒙古大学图书馆

18th IEEE India Council International Conference, INDICON 2021

作者： Chandni, M. Govind, D. Center for Computational Engineering and Networking Tamilnadu Amritanagar Coimbatore 641112 India Department of Computer Science Engineering Andhra Pradesh Greenfields Vaddeswaram Guntur 522501 India

ISBN: (纸本)9781665441759

Epochs are impulse like discontinuities in speech that represent the instants of glottal closure during phonation. The accurate estimation of epochs is essential for epoch synchronous speech processing. There are many algorithms proposed in the literature for the accurate estimation of epochs from speech signals. However majority of those algorithms show degradation during the epoch extraction from telephonic speech signals. The restricted bandwidth (300 Hz-3.4 kHz) of the telephone channel is the reason for degradation in epoch estimation performance. Therefore, the objective of the present work is to propose a wavelet synchrosqueezed transform (WSST) based signal preprocessing stage to improve the performance of zero frequency filtering (ZFF) which is a well known epoch estimation method. Improved time-frequency resolution of WSST reinforce the strength of impulses around the fundamental components to estimate accurate epoch locations. A multiscale product of WSST modified speech and the original speech is computed further enhance the impulse like discontinuities. Effectiveness of the proposed method is confirmed by the epoch estimation performance analysis of phonetically balanced CMU-Arctic database with electroglottogram recordings. The telephone quality in the database is simulated using G.191 software tools. © 2021 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Fast-RF-Shimming: Accelerate RF Shimming in 7T MRI using Deep Learning

arXiv

引用

arXiv 2025年

作者： Lu, Zhengyi Liang, Hao Lu, Ming Wang, Xiao Yan, Xinqiang Huo, Yuankai Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States Vanderbilt University Institute of Imaging Science Vanderbilt University Medical Center NashvilleTN United States Department of Radiology and Radiological Sciences Vanderbilt University Medical Center NashvilleTN United States Computational Science and Engineering Division Oak Ridge National Laboratory Oak RidgeTN United States Department of Computer Science Vanderbilt University NashvilleTN United States

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. How- ever, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field (B+1 ) inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate B+1 inhomogeneity but remain time-consuming and typically require the patient’s presence to compute solutions. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000× speed-up in RF shimming compared to traditional MLS optimization methods. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel B+1 fields. Next, we train a Residual Network (ResNet) to map B+1 fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. By leveraging a residual learning paradigm, our approach circumvents the need for pre-computed reference solutions in the testing phase and remarkably reduces computational overhead. Comparative evaluations with standard MLS optimization underscore notable gains in both processing s

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

EvcenterNet: Uncertainty Estimation for Object Detection Using Evidential Learning

EvCenterNet: Uncertainty Estimation for Object Detection Usi...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Monish R. Nallapareddy Kshitij Sirohi Paulo L. J. Drews Wolfram Burgard Chih-Hong Cheng Abhinav Valada Fraunhofer IKS Germany Department of Computer Science University of Freiburg Germany Computational Science Center Federal University of Rio Grande Brazil Department of Engineering University of Tech. Nuremberg Germany TU München Germany

Uncertainty estimation is crucial in safety-critical settings such as automated driving as it provides valuable information for several downstream tasks including high-level decision making and path planning. In this work, we propose EvcenterNet, a novel uncertainty-aware 2D object detection framework using evidential learning to directly estimate both classification and regression uncertainties. To employ evidential learning for object detection, we devise a combination of evidential and focal loss functions for the sparse heatmap inputs. We introduce class-balanced weighting for regression and heatmap prediction to tackle the class imbalance encountered by evidential learning. Moreover, we propose a learning scheme to actively utilize the predicted heatmap uncertainties to improve the detection performance by focusing on the most uncertain points. We train our model on the KITTI dataset and evaluate it on challenging out-of-distribution datasets including BDD100K and nuImages. Our experiments demonstrate that our approach improves the precision and minimizes the execution time loss in relation to the base model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Original Article: A New Method for Optimal Solution of Intuitionistic Fuzzy Transportation Problems via Generalized Trapezoidal Intuitionistic Fuzzy Numbers

引用

Fuzzy Information and Engineering 2024年第1期11卷 105-120页

作者： Darunee Hunwisai Poom Kumam Wiyada Kumam Department of Applied Mathematics Faculty of Science and Technology Valaya Alongkorn Rajabhat University under the Royal Patronage Pathumthani Thailand Science Laboratory Building Faculty of Science KMUTT-Fixed Point Theory and Applications Research Group (KMUTT-FPTA) Theoretical and Computational Science Center (TaCS) King Mongkut's University of Technology Thonburi (KMUTT) Bangkok Thailand Department of Mathematics and Computer Science Faculty of Science and Technology Rajamangala University of Technology Thanyaburi Pathumthani Thailand

In this paper, we introduce the new method for solving the intuitionistic fuzzy transportation problem (IFTP), by using north-west corner method and modified distribution method to find the optimal solution for IFTP.

关键词： Costs Shape Transportation

来源：评论

学校读者我要写书评

暂无评论

What can real information content tell us about compressing climate model data? 8

What can real information content tell us about compressing ...

引用

8th IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data, DRBSD-8 2022

作者： Sather, Hayden Pinard, Alexander Baker, Allison H. Hammerling, Dorit M. Colorado School of Mines Department of Computer Science GoldenCO United States Applied Mathematics and Statistics Colorado School of Mines GoldenCO United States Computational and Information Systems Lab National Center for Atmospheric Research BoulderCO United States

ISBN: (纸本)9781665463379

The massive data volumes produced by climate simulation models create an urgent need for data reduction. Lossy compression in particular is a solution that can significantly reduce storage requirements, however, a tradeoff must be made between the amount of compression applied and the scientific integrity of the data. Determining how much compression can be applied is therefore vital for applying lossy compression. One particular metric for gauging the quality of compression is the percentage of real information present in the original data that is preserved in the compressed data. We compute bitwise real information content for several climate variables from the popular Community Earth System Model, and we investigate the amount of compression that can be applied to each of these climate variables using two popular compression algorithms designed for floating-point data while preserving 99% of the real information content. The analysis of the real information content of data after lossy compression has been applied shows a helpful visualization of how compression artifacts have been introduced to the data. Finally, we demonstrate how this real information content can be used in a straightforward manner to determine compressor settings for our data. © 2022 IEEE.

关键词： Climate models

来源：评论

学校读者我要写书评

暂无评论

A Scalable Training-Free Diffusion Model for Uncertainty Quantification 24

A Scalable Training-Free Diffusion Model for Uncertainty Qua...

引用

Proceedings of the SC '24 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis

作者： Ali Haisam Muhammad Rafid Junqi Yin Yuwei Geng Siming Liang Feng Bao Lili Ju Guannan Zhang Department of Computer Science Virginia Polytechnic Institute and State University Blacksburg VA USA National Center of Computational Science Oak Ridge National Laboratory Oak Ridge TN USA Department of Mathematics University of South Carolina Columbia SC USA Department of Mathematics Florida State University Tallahassee FL USA Computer Science and Math Division Oak Ridge National Laboratory Oak Ridge TN USA

ISBN: (纸本)9798350355543

Generative artificial intelligence extends beyond its success in image/text synthesis, proving itself a powerful uncertainty quantification (UQ) technique through its capability to sample from complex high-dimensional probability distributions. However, existing methods often require a complicated training process, which greatly hinders their applications to real-world UQ problems, especially in dynamic UQ tasks where the target probability distribution evolves rapidly with time. To alleviate this challenge, we have developed a scalable, training-free score-based diffusion model for high-dimensional sampling. We incorporate a parallel-in-time method into our diffusion model to use a large number of GPUs to solve the backward stochastic differential equation and generate new samples of the target distribution. Moreover, we also distribute the computation of the large matrix subtraction used by the training-free score estimator onto multiple GPUs available across all nodes. Compared to existing methods, our approach completely avoids training the score function, making it capable of adapting to rapid changes in the target probability distribution. We showcase the remarkable strong and weak scaling capabilities of the proposed method on the Frontier supercomputer, as well as its uncertainty reduction capability in hurricane predictions when coupled with AI-based foundation models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QAUST:Protein Function Prediction Using Structure Similarity,Protein Interaction,and Functional Motifs

引用

Genomics, Proteomics & Bioinformatics 2021年第6期19卷 998-1011页

作者： Fatima Zohra Smaili Shuye Tian Ambrish Roy Meshari Alazmi Stefan T.Arold Srayanta Mukherjee P.Scott Hefty Wei Chen Xin Gao Computational Bioscience Research Center(CBRC) ComputerElectrical and Mathematical Sciences and Engineering(CEMSE)DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955Saudi Arabia Department of Biology Southern University of Science and Technology of China(SUSTC)Shenzhen 518055China Department of Computational Medicine and Bioinformatics University of MichiganAnn ArborMI 48109USA College of Computer Science and Engineering University of Ha’ilHa'il 55476Saudi Arabia Biological and Environmental Sciences and Engineering(BESE)Division King Abdullah University of Science and Technology(KAUST)Thuwal 23955Saudi Arabia Department of Molecular Bioscience University of KansasLawrenceKS 66047USA

The number of available protein sequences in public databases is increasing ***,a sig-nificant percentage of these sequences lack functional annotation,which is essential for the understanding of how bio-logical systems ***,we propose a novel method,Quantitative Annotation of Unknown STructure(QAUST),to infer protein functions,specifically Gene Ontology(GO)terms and Enzyme Commission(EC)*** uses three sources of information:structure information encoded by global and local structure similarity search,biological network information inferred by protein–protein interaction data,and sequence information extracted from functionally discriminative sequence *** three pieces of information are combined by consensus averaging to make the final *** approach has been tested on 500 protein targets from the Critical Assessment of Functional Annotation(CAFA)benchmark *** results show that our method provides accurate functional annotation and outperforms other prediction methods based on sequence similarity search or *** further demonstrate that a previously unknown function of human tripartite motif-containing 22(TRIM22)protein predicted by QAUST can be experimentally validated.

关键词： Protein function prediction GO term EC number Protein structure similarity Functionally discriminative motif

来源：评论

学校读者我要写书评

暂无评论

Single-cell multi-ome regression models identify functional and disease-associated enhancers and enable chromatin potential analysis (vol 56, pg 627, 2024)

引用

NATURE GENETICS 2024年第6期56卷 1319-1319页

作者： Mitra, Sneha Malik, Rohan Wong, Wilfred Rahman, Afsana Hartemink, Alexander J. Pritykin, Yuri Dey, Kushal K. Leslie, Christina S. Computational and Systems Biology Program Memorial Sloan Kettering Cancer Center New York City NY USA Rye Country Day School Rye NY USA Tri-Institutional Training Program in Computational Biology and Medicine New York City NY USA Hunter College City University of New York New York City NY USA Department of Computer Science Duke University Durham NC USA Program in Computational Biology and Bioinformatics Duke University Durham NC USA Center for Genomic and Computational Biology Duke University Durham NC USA Department of Computer Science Princeton University Princeton NJ USA Lewis-Sigler Institute for Integrative Genomics Princeton University Princeton NJ USA

We present a gene-level regulatory model, single-cell ATAC + RNA linking (SCARlink), which predicts single-cell gene expression and links enhancers to target genes using multi-ome (scRNA-seq and scATAC–seq co-assay) sequencing data. The approach uses regularized Poisson regression on tile-level accessibility data to jointly model all regulatory effects at a gene locus, avoiding the limitations of pairwise gene–peak correlations and dependence on peak calling. SCARlink outperformed existing gene scoring methods for imputing gene expression from chromatin accessibility across high-coverage multi-ome datasets while giving comparable to improved performance on low-coverage datasets. Shapley value analysis on trained models identified cell-type-specific gene enhancers that are validated by promoter capture Hi-C and are 11× to 15× and 5× to 12× enriched in fine-mapped eQTLs and fine-mapped genome-wide association study (GWAS) variants, respectively. We further show that SCARlink-predicted and observed gene expression vectors provide a robust way to compute a chromatin potential vector field to enable developmental trajectory analysis.

关键词： Epigenetics Population genetics Software

来源：评论

学校读者我要写书评

暂无评论

Best Practices for a Handwritten Text Recognition System

arXiv

引用

arXiv 2024年

作者： Retsinas, George Sfikas, Giorgos Gatos, Basilis Nikou, Christophoros School of Electrical and Computer Engineering National Technical University of Athens Greece Computational Intelligence Laboratory Institute of Informatics and Telecommunications National Center for Scientific Research "Demokritos" Greece Department of Computer Science and Engineering University of Ioannina Greece Department of Surveying and Geoinformatics Engineering University of West Attica Greece

Handwritten text recognition has been developed rapidly in the recent years, following the rise of deep learning and its applications. Though deep learning methods provide notable boost in performance concerning text recognition, non-trivial deviation in performance can be detected even when small pre-processing or architectural/optimization elements are changed. This work follows a "best practice" rationale;highlight simple yet effective empirical practices that can further help training and provide well-performing handwritten text recognition systems. Specifically, we considered three basic aspects of a deep HTR system and we proposed simple yet effective solutions: 1) retain the aspect ratio of the images in the preprocessing step, 2) use max-pooling for converting the 3D feature map of CNN output into a sequence of features and 3) assist the training procedure via an additional CTC loss which acts as a shortcut on the max-pooled sequential features. Using these proposed simple modifications, one can attain close to state-of-the-art results, while considering a basic convolutional-recurrent (CNN+LSTM) architecture, for both IAM and RIMES datasets. Code is available at https://***/georgeretsi/HTR-best-practices/. © 2024, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A PEPS Plugin for TNQVM

A PEPS Plugin for TNQVM

引用

Quantum Computing and Engineering (QCE), IEEE International Conference on

作者： Srikar Chundury Justin Lietz Eduardo Antonio Coello Pérez Amir Shehata In-Saeng Suh Frank Mueller Department of Computer Science North Carolina State University Raleigh NC USA National Center for Computational Sciences Oak Ridge National Laboratory Oak Ridge TN USA

This work introduces an extension to the Tensor Network Quantum Virtual Machine (TNQVM) tool, enhancing the existing stack of ExaScale Tensor Network (ExaTN), ExaScale Accelerator (XACC), and TNQVM. It features a new plugin that enables efficient simulation of a Projected Entangled Pair State (PEPS), a 2D tensor network. To improve simulation efficiency for PEPS, we have implemented the snake boundary contraction algorithm. By integrating this capability into the existing stack, we enhance the overall functionality and versatility of the framework. We tested this new PEPS topology for a simple GHZ bell-pair generation quantum circuit and saw that its runtime is very close to that of the MPS topology. We estimate that the real potential of the PEPS topology becomes discernible when quantum circuits with multidimensional entanglement are simulated using tensor networks. In such cases, 1D tensor networks fail to represent or contract them efficiently.

关键词：

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：