检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y.F. Scarlett, Jonathan Descartes Program CNRS@CREATE 138602 Singapore Department of Information Systems and Analytics School of Computing National University of Singapore 119077 Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore 119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank–Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ *** Codes 68T05 Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A volumetric change detection framework using UAV oblique photogrammetry - A case study of ultra-high-resolution monitoring of progressive building collapse

arXiv

引用

arXiv 2021年

作者： Xu, Ningli Huang, Debao Song, Shuang Ling, Xiao Strasbaugh, Chris Yilmaz, Alper Sezen, Halil Qin, Rongjun Geospatial Data Analytics Lab The Ohio State University Columbus United States Photogrammetric Computer Vision Lab The Ohio State University Columbus United States Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus United States Department of Electrical and Computer Engineering The Ohio State University Columbus United States Translational Data Analytics Institute The Ohio State University Columbus United States Engineering Technology Services The Ohio State University Columbus United States

In this paper, we present a case study that performs an unmanned aerial vehicle (UAV) based fine-scale 3D change detection and monitoring of progressive collapse performance of a building during a demolition event. Multi-temporal oblique photogrammetry images are collected with 3D point clouds generated at different stages of the demolition. The geometric accuracy of the generated point clouds has been evaluated against both airborne and terrestrial LiDAR point clouds, achieving an average distance of 12 cm and 16 cm for roof and façade respectively. We propose a hierarchical volumetric change detection framework that unifies multi-temporal UAV images for pose estimation (free of ground control points), reconstruction, and a coarse-to-fine 3D density change analysis. This work has provided a solution capable of addressing change detection on full 3D time-series datasets where dramatic scene content changes are presented progressively. Our change detection results on the building demolition event have been evaluated against the manually marked ground-truth changes and have achieved an F-1 score varying from 0.78 to 0.92, with consistently high precision (0.92 - 0.99). Volumetric changes through the demolition progress are derived from change detection and have shown to favorably reflect the qualitative and quantitative building demolition progression. Copyright © 2021, The Authors. All rights reserved.

关键词： Photogrammetry

来源：评论

学校读者我要写书评

暂无评论

NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-task Financial Forecasting

arXiv

引用

arXiv 2022年

作者： Yang, Linyi Li, Jiazheng Dong, Ruihai Zhang, Yue Smyth, Barry Westlake Institute for Advanced Study Westlake University China School of Engineering Westlake University China The Insight Centre for Data Analytics University College Dublin Ireland Department of Computer Science University of Warwick United Kingdom

Financial forecasting has been an important and active area of machine learning research because of the challenges it presents and the potential rewards that even minor improvements in prediction accuracy or forecasting may entail. Traditionally, financial forecasting has heavily relied on quantitative indicators and metrics derived from structured financial statements. Earnings conference call data, including text and audio, is an important source of unstructured data that has been used for various prediction tasks using deep earning and related approaches. However, current deep learning-based methods are limited in the way that they deal with numeric data;numbers are typically treated as plain-text tokens without taking advantage of their underlying numeric structure. This paper describes a numeric-oriented hierarchical transformer model (NumHTML) to predict stock returns, and financial risk using multimodal aligned earnings calls data by taking advantage of the different categories of numbers (monetary, temporal, percentages etc.) and their magnitude. We present the results of a comprehensive evaluation of NumHTML against several state-of-the-art baselines using a real-world publicly available dataset. The results indicate that NumHTML significantly outperforms the current state-of-the-art across a variety of evaluation metrics and that it has the potential to offer significant financial gains in a practical trading context. © 2022, CC BY-NC-ND.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation

arXiv

引用

arXiv 2024年

作者： Zhang, Pengfei Li, Chang Zhang, Yongjun Qin, Rongjun Key Laboratory for Geographical Process Analysis & Simulation of Hubei Province College of Urban and Environmental Science Central China Normal University Wuhan China School of Remote Sensing and Information Engineering Wuhan University China Department of Civil Environmental and Geodetic Engineering Department of Electrical and Computer Engineering Translational Data Analytics Institute The Ohio State University ColumbusOH United States

Remotely sensed imagery interpretation (RSII), including semantic segmentation and change detection, faces the three major problems: (1) objective representation of spatial distribution patterns with coexistence of spatial stationary and non-stationary;(2) edge uncertainty problem caused by downsampling encoder and intrinsic edge noises (e.g., mixed pixel and edge occlusion etc.);and (3) false detection problem caused by geometric registration error in change detection. To solve the aforementioned problems, uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the first to be proposed, whose superiorities are as follows: (1) a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP) is proposed to enhance the interaction of spatially frequency-wise stationary and non-stationary features to yield high-fidelity edge extraction result. Inspired by HRFormer, SHCP proposes high-frequency-wise stream to replace high-resolution-wise stream in HRFormer through the whole encoder-decoder process with parallel frequency-wise high-to-low streams, so it improves the edge extraction accuracy by continuously remaining high-frequency information;(2) a mask-and-geo-knowledge-based uncertainty diffusion module (MUDM), which is a self-supervised learning strategy, is proposed to improve the edge accuracy of extraction and change detection by gradually removing the simulated spectrum noises based on geo-knowledge and the generated diffused spectrum noises;(3) a frequency-wise semi-pseudo-Siamese UDHF2-Net is the first to be proposed to balance accuracy and complexity for change detection. Besides the aforementioned spectrum noises in semantic segmentation, MUDM is also a self-supervised learning strategy to effectively reduce the edge false change detection from the generated imagery with geometric registration error. In semantic segmentation experiments, UDHF2-Net achieved the best mIoU values of 92.00%, 87.31% and 55.27% respecti

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Ranking-based convolutional neural network models for peptide-MHC binding prediction

arXiv

引用

arXiv 2020年

作者： Chen, Ziqi Min, Martin Renqiang Ning, Xia Computer Science and Engineering Department Ohio State University ColumbusOH United States Machine Learning Department NEC Labs America PrincetonNJ United States Biomedical Informatics Department Ohio State University ColumbusOH United States Translational Data Analytics Institute Ohio State University ColumbusOH United States

T-cell receptors can recognize foreign peptides bound to major histocompatibility complex (MHC) class-I proteins, and thus trigger the adaptive immune response. Therefore, identifying peptides that can bind to MHC class-I molecules plays a vital role in the design of peptide vaccines. Many computational methods, for example, the state-of-the-art allele-specific method MHCflurry, have been developed to predict the binding affinities between peptides and MHC molecules. In this manuscript, we develop two allele-specific Convolutional Neural Network (CNN)based methods named ConvM and SpConvM to tackle the binding prediction problem. Specifically, we formulate the problem as to optimize the rankings of peptide-MHC bindings via ranking-based learning objectives. Such optimization is more robust and tolerant to the measurement inaccuracy of binding affinities, and therefore enables more accurate prioritization of binding peptides. In addition, we develop a new position encoding method in ConvM and SpConvM to better identify the most important amino acids for the binding events. We conduct a comprehensive set of experiments using the latest Immune Epitope database (IEDB) datasets. Our experimental results demonstrate that our models significantly outperform the state-of-the-art methods including MHCflurry with an average percentage improvement of 6.70% on AUC and 17.10% on ROC5 across 128 alleles. © 2020, CC BY.

关键词： Peptides

来源：评论

学校读者我要写书评

暂无评论

Forecasting Thailand’s Precipitation with Cascading Model of CNN and GRU

Forecasting Thailand’s Precipitation with Cascading Model o...

引用

International Conference on Information Technology and Electrical engineering (ICITEE)

作者： Fuenglada Manokij Kanoksri Sarinnapakorn Peerapon Vateekul Department of Computer Engineering Faculty of Engineering Chulalongkorn University Big Data Analytics and IoT Center (CUBIC) Chulalongkorn University Bangkok Thailand Hydro-Informatics Institute (Public Organization) Ministry of Higher Education Science Research and Innovation Bangkok Thailand

Precipitation prediction is necessary to use in water management, especially in Thailand, it can be applied for various ways, such as flood warning, agriculture planning, etc. There are many prior attempts to forecast rainfall from the rain-gauge station. Some deployed traditional machine learning approaches: ARIMA, k-NN, etc. Recently, deep learning approach has shown promising results in this task. However, the accuracy is still limited since the raining period throughout the year in Thailand is very scarce, so most rainfall amount is zero. In this paper, we propose to cascade two deep learning networks to tackle this problem: one is a classification model to classify whether it rains or not, and the other is a regression model to predict rainfall amount. Our network is a combination of CNN and GRU, where CNN aims to capture relationship between various sensors and GRU aims to capture time-series information. Furthermore, we also perform multi-step forecasting by applying a rolling mechanism that uses the predicted rainfall and involved features to predict the next 6 steps. The experiment was conducted on hourly rainfall dataset for 6 years (2013-2018) provided from the public government sector in Thailand. We use RMSE as performance metric to evaluate three periods of rainfall: Overall, Rain, and non-rain periods and the results show that our cascading model is the winner with only 4.53% in term of RMSE which is the average percentage of difference from over all regions.

关键词： Deep learning Rain Predictive models data models Sensors Forecasting Task analysis

来源：评论

学校读者我要写书评

暂无评论

Reservoir Water Level Forecasting using Deep Learning

Reservoir Water Level Forecasting using Deep Learning

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Archita Mallick Surajit Ghosh Kounik De Sarkar Sudip Roy Centre of Excellence in Disaster Mitigation and Management Indian Institute of Technology Roorkee Roorkee India Water Futures Data and Analytics International Water Management Institute Colombo Sri Lanka Environmental Science and Engineering Department Indian Institute of Technology Bombay Mumbai India Department of Computer Science and Engineering Indian Institute of Technology Roorkee Roorkee India

ISBN: (数字)9798350390346

ISBN: (纸本)9798350390353

Reservoirs play a vital role in water resource management and provide essential ecosystem services. The study focuses on extracting the water extent of Maithon reservoir, Jharkhand, India, from 2017 to 2023 by delineating the boundaries between the water and non-water class extracted from Sentinel-1 data. The scenes were processed using Google Earth Engine to obtain water extent using the Otsu method. This research extends the application of the extracted water extent values, precipitation data from CHIRPS, and weekly historical water level data of the reservoir obtained from the Central Water Commission to monthly forecasts of the water level using the Long Short-Term Memory (LSTM) model. The forecasts were obtained with a mean absolute error of around 80 cm with test data. The study provides initial results and is under further modification, where the improved estimation shall be integrated into flood early warning systems and help to provide actionable insights to stakeholders and decision-makers to mitigate risks and optimize water usage.

关键词： Precipitation Ecosystems Sentinel-1 Alarm systems Reservoirs Floods data mining Stakeholders Long short term memory Streams

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Multi-Block Deep CNN

Facial Expression Recognition Using Multi-Block Deep CNN

引用

International Conference on Circuits, Communication, Control and Computing

作者： Priyadarshini V Srinivasulu Reddy U Venkata Rami Reddy Chirra Mrudula M Suneetha M Dept. of Computer Science & Engineering National Institute of Technology Andhra Pradesh India Dept. of Computer Applications Machine Learning & Data Analytics lab National Institute of Technology Tiruchirappalli India School of Computer Science & Engineering VIT-AP University Amaravathi India Department of CSE Malla Reddy College of Engineering Telangana India Independent Researcher Amaravati India

ISBN: (数字)9798331528539

ISBN: (纸本)9798331528546

Emotions play a crucial role in decision-making, moral judgments, and other cognitive processes. The goal of this work is to identify people's facial emotions from face images. Facial expression recognition (FER), a highly diverse field with many commonalities between classes, is a challenging problem. The capabilities of current FER systems are limited in this regard. In this work, a multi-block Deep Convolutional Neural Networks (DCNN) model was proposed to identify facial expressions. Five blocks with different computational components were defined in a multi-block DCNN to extract the unique characteristics from input images. The second model (DCNN-SVM) is developed with an ensemble of SVM classifier to improve predictability and stability. The third model (DCNN-MV) is based on the majority voting with 4 classifiers SVM, KNN, Random Forest, and Decision Tree. The CK+ dataset was utilized and expanded via image data augmentation to enhance model performance and generalization. By adjusting hyperparameters, the suggested DCNN model's accuracy was investigated. The DCNN model reports an accuracy score of 97.71%. Both DCNN-SVM and DCNN-MV models achieved 97.79% accuracy. On the CK+ dataset, the proposed models demonstrated good accuracy in identifying facial expressions. When compared to existing models, the proposed model outperformed existing models in terms of accuracy.

关键词： Support vector machines Accuracy Computational modeling Face recognition Stability analysis Circuit stability Convolutional neural networks Integrated circuit modeling Thermal stability Random forests

来源：评论

学校读者我要写书评

暂无评论

Multimodal Subspace Independent Vector Analysis Better Captures Hidden Relationships in Multimodal Neuroimaging data

Multimodal Subspace Independent Vector Analysis Better Captu...

引用

IEEE International Symposium on Biomedical Imaging

作者： Xinhui Li Tulay Adali Rogers F. Silva Vince D. Calhoun Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University Georgia Institute of Technology and Emory University Atlanta GA USA Department of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD USA

We introduce multimodal subspace independent vector analysis (MSIVA), a methodology to capture both joint and unique latent sources across data modalities by defining shared and modality-specific subspaces. We compared MSIVA to a unimodal analysis (UA) baseline and tested both methods with four distinct subspace structures on synthetic and multimodal neuroimaging datasets. We demonstrated that both approaches can identify and distinguish the correct subspace structures from incorrect ones on synthetic datasets. We then showed that MSIVA can better capture the subspace structures across two neuroimaging modalities. Results from subsequent per-subspace canonical correlation analysis and brain-phenotype modeling showed that the sources from the optimal subspace structure are significantly associated with phenotype measures including age and sex.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A structural haplotype in the 17q21.31 MAPT region is associated with increased risk for chronic traumatic encephalopathy endophenotypes

Cell Reports Medicine

引用

Cell Reports Medicine 2025年第5期6卷 102084-102084页

作者： Han, Xudong Zhang, Yichi Petrosky, Jillian N. Bald, Sarah Sherva, Richard M. Labadorf, Adam Cherry, Jonathan D. Chung, Jaeyoon Farrell, Kurt Abdolmohammadi, Bobak Durape, Shruti Martin, Brett M. Palmisano, Joseph N. Farrell, John J. Alvarez, Victor E. Huber, Bertrand R. Dwyer, Brigid Daneshvar, Daniel H. Jun, Gyungah R. Lunetta, Kathryn L. Goldstein, Lee E. Katz, Douglas I. Cantu, Robert C. Shenton, Martha E. Cummings, Jeffrey L. Reiman, Eric M. Stern, Robert A. Alosco, Michael L. Tripodis, Yorghos Farrer, Lindsay A. Stein, Thor D. Crary, John F. McKee, Ann C. Mez, Jesse Bioinformatics Graduate Program Boston University Boston MA United States Section of Biomedical Genetics Department of Medicine Boston University Chobanian & Avedisian School of Medicine Boston MA United States Department of Neurology Boston University Chobanian & Avedisian School of Medicine Boston MA United States Boston University Alzheimer's Disease Research Center Boston University Chobanian & Avedisian School of Medicine Boston MA United States Boston VA Healthcare System Boston MA United States Boston University Chronic Traumatic Encephalopathy Center Boston University Boston MA United States Department of Pathology and Laboratory Medicine Boston University Chobanian & Avedisian School of Medicine Boston MA United States Departments of Pathology Neuroscience and Artificial Intelligence & Human Health Neuropathology Brain Bank & Research CoRE Friedman Brain Institute Ronald M. Loeb Center for Alzheimer's Disease Icahn School of Medicine at Mount Sinai New York NY United States Biostatistics and Epidemiology Data Analytics Center Boston University School of Public Health Boston MA United States Bedford VA Healthcare System Bedford MA United States Braintree Rehabilitation Hospital Braintree MA United States Department of Physical Medicine and Rehabilitation Harvard Medical School Boston MA United States Department of Rehabilitation and Human Performance Brain Injury Research Center Icahn School of Medicine at Mount Sinai New York NY United States Department of Neurology Icahn School of Medicine at Mount Sinai New York NY United States Department of Biostatistics Boston University School of Public Health Boston MA United States Department of Ophthalmology Boston University Chobanian & Avedisian School of Medicine Boston MA United States Departments of Biomedical Electrical & Computer Engineering Boston University College of Engineering Boston MA United States Departments of Radiology and Psychiatry Boston University Chobanian & Avedisia

Chronic traumatic encephalopathy (CTE) is a neurodegenerative tauopathy associated with repetitive head impact (RHI) exposure. Genetic variation in the 17q21.31 region, containing microtubule-associated protein tau (MAPT), has been implicated in tauopathies but has not been investigated in CTE. The region includes a megabase-long inversion (H1/H2) and copy-number variations, including α, β, and γ segments, which can be characterized as nine segregating structural haplotypes. We leveraged array SNP data and a reference panel across the 17q21.31 region to impute structural haplotypes and test their association with CTE endophenotypes in 447 European ancestry brain donors with RHI exposure. The H1β1γ1 haplotype was significantly associated with dementia and semi-quantitative tau burden in multiple cortical and medial temporal regions commonly affected in CTE. H1β1γ1 differential expression analyses in dorsolateral frontal cortex implicated cis-acting genes and inflammatory pathways. Taken together, the H1β1γ1 haplotype may help explain CTE heterogeneity among those with similar RHI exposure. © 2025 The Authors

关键词： 17q21.31 chronic traumatic encephalopathy dementia differential gene expression immune system MAPT repetitive head impacts structural haplotypes tauopathy traumatic brain injury

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：