检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hu, Haichen Ai, Rui Bates, Stephen Simchi-Levi, David Center for Computational Science and Engineering MIT United States Institute for Data Systems and Society MIT United States Department of EECS MIT United States Department of Civil and Environmental Engineering MIT United States

Contextual sequential decision-making problems play a crucial role in machine learning, encompassing a wide range of downstream applications such as bandits, sequential hypothesis testing and online risk control. These applications often require different statistical measures, including expectation, variance and quantiles. In this paper, we provide a universal admissible algorithm framework for dealing with all kinds of contextual online decision-making problems that directly learns the whole underlying unknown distribution instead of focusing on individual statistics. This is much more difficult because the dimension of the regression is uncountably infinite, and any existing linear contextual bandits algorithm will result in infinite regret. To overcome this issue, we propose an efficient infinite-dimensional functional regression oracle for contextual cumulative distribution functions (CDFs), where each data point is modeled as a combination of context-dependent CDF basis functions. Our analysis reveals that the decay rate of the eigenvalue sequence of the design integral operator governs the regression error rate and, consequently, the utility regret rate. Specifically, when the eigenvalue sequence exhibits a polynomial decay of order γ1 ≥ 1, the utility regret is bounded by (formula presented) By setting γ = 0, this recovers the existing optimal regret rate for contextual bandits with finite-dimensional regression and is optimal under a stronger exponential decay assumption. Additionally, we provide a numerical method to compute the eigenvalue sequence of the integral operator, enabling the practical implementation of our framework. © 2025, CC BY.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Personalized Stress Detection using a Lightweight Machine Learning Framework With Convenient Wrist-Worn Sensors

Personalized Stress Detection using a Lightweight Machine Le...

引用

2024 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2024

作者： Hasan, M. Mithun, S. Mahmud, M. Baral, S. Poudel, K. Middle Tennessee State University Computational And Data Science MurfreesboroTN United States University Of Memphis Dept. Of Computer Science TN United States University Of Memphis Dept. Of Electrical And Computer Engineering TN United States Middle Tennessee State University Dept. Of Computer Science MurfreesboroTN United States Univ. Of Tennessee Health Science Center Div. Of General Internal Medicine MemphisTN United States

ISBN: (纸本)9798350388572

Over 70% Americans experience daily stress, making real-time, accurate stress detection crucial for timely intervention, and promoting physical and mental well-being. In this study, we detect stress using machine learning from publicly available wrist-worn sensor data. We examined both population and individual levels, focusing on simple, computation friendly statistical features for reduced processing to facilitate adoptions in real-life mHealth applications. Our framework demonstrates that stress detection achieves over 96% accuracy at both the population and individual levels, with the Extreme Gradient Boosting classifier achieving the highest predictive accuracy. We found significant variability between individuals and achieved an average accuracy of 99.63% with area under the curve (AUC) 99.23%, F1-score 99.00%, precision, and recall 99.22%. This approach offers a promising solution for real-life stress detection due to its high accuracy and simplicity. © 2024 IEEE.

关键词： LightGBM Machine learning Personalization Stress detection Wrist-band sensors

来源：评论

学校读者我要写书评

暂无评论

MultiPanoWise: holistic deep architecture for multi-task dense prediction from a single panoramic image

MultiPanoWise: holistic deep architecture for multi-task den...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Uzair Shah Muhammad Tukur Mahmood Alzubaidi Giovanni Pintore Enrico Gobbetti Mowafa Househ Jens Schneider Marco Agus ICT Division College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Visual and Data-Intensive Computing CRS4 Italy National Research Center in HPC Big Data and Quantum Computing Italy

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

We present a novel holistic deep-learning approach for multi-task learning from a single indoor panoramic image. Our framework, named MultiPanoWise, extends vision transformers to jointly infer multiple pixel-wise signals, such as depth, normals, and semantic segmentation, as well as signals from intrinsic decomposition, such as reflectance and shading. Our solution leverages a specific architecture combining a transformer-based encoder-decoder with multiple heads, by introducing, in particular, a novel context adjustment approach, to enforce knowledge distillation between the various signals. Moreover, at training time we introduce a hybrid loss scalarization method based on an augmented Chebychev/hypervolume scheme. We illustrate the capabilities of the proposed architecture on public-domain synthetic and real-world datasets. We demonstrate performance improvements with respect to the most recent methods specifically designed for single tasks, like, for example, individual depth estimation or semantic segmentation. To our knowledge, this is the first architecture capable of achieving state-of-the-art performance on the joint extraction of heterogeneous signals from single indoor omnidirectional images.

关键词： Training Reflectivity Computer vision Semantic segmentation Estimation Computer architecture Multitasking

来源：评论

学校读者我要写书评

暂无评论

Gastric residual volume as predictor of clinical outcomes in critically ill patients at nutritionday: A machine learning (ML) approach

引用

Clinical Nutrition ESPEN 2023年 58卷 452-453页

作者： Raphaeli, O. Ben Yechiel, L. Statlander, L. Kagan, I. Hiesmayr, M. Tarantino, S. Worf, I. Knoetzl, A. Singer, P. Industrial Engineering and Management Ariel University Ariel Intensive Care Unit Rabin Medical Center Petah Tikva Israel CeDAS (Center for Medical Data Science) Medical University Vienna Vienna Austria

来源：评论

学校读者我要写书评

暂无评论

BIM: Improving Graph Neural Networks with Balanced Influence Maximization 40

BIM: Improving Graph Neural Networks with Balanced Influence...

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhang, Wentao Gao, Xinyi Yang, Ling Cao, Meng Huang, Ping Shan, Jiulong Yin, Hongzhi Cui, Bin Peking University Center for Machine Learning Research China Institute of Advanced Algorithms Research Shanghai China National Engineering Labratory for Big Data Analytics and Applications The University of Queensland Australia Peking University Key Lab of High Confidence Software Technologies China Apple Inc. Institute of Computational Social Science Peking University Qingdao China

ISBN: (纸本)9798350317152

The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A study of first-passage time minimization via Q-learning in heated gridworlds

arXiv

引用

arXiv 2021年

作者： Larchenko, Maria A. Osinenko, P. Yaremenko, G. Palyulin, V.V. Center for Computational and Data-intensive Science and Engineering Skolkovo Institute of Science and Technology Moscow121205 Russia

Optimization of first-passage times is required in applications ranging from nanobots navigation to market trading. In such settings, one often encounters unevenly distributed noise levels across the environment. We extensively study how a learning agent fares in 1- and 2- dimensional heated gridworlds with an uneven temperature distribution. The results show certain bias effects in agents trained via simple tabular Q-learning, SARSA, Expected SARSA and Double Q-learning. While high learning rate prevents exploration of regions with higher temperature, low enough rate increases the presence of agents in such regions. The discovered peculiarities and biases of temporal-difference-based reinforcement learning methods should be taken into account in real-world physical applications and agent design. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Structural Dynamics in Retracted and Non-Retracted Author’s Collaboration Networks: A Quantitative Analysis

arXiv

引用

arXiv 2024年

作者： Sharma, Kiran Sharma, Aanchal Jose, Jazlyn Saini, Vansh Sobti, Raghavraj Uddin, Ziya School of Engineering & Technology BML Munjal University Haryana Gurugram122413 India Center for Advanced Data and Computational Science BML Munjal University Haryana Gurugram122413 India

Retractions compromise the reliability of the scientific literature and affect the foundation of further research. Understanding the structure of collaboration networks in retracted papers helps identify risk factors, such as recurring co-authors or institutions. To compare the network structures of retracted and non-retracted networks, we selected 30 authors with a sufficiently large number of retractions. The number of retracted papers for each author was obtained from the Retraction Watch database, while non-retracted papers were sourced from the Scopus database. Using this data, collaboration networks for retracted and non-retracted authors were constructed. To analyze the dynamics between these networks, various network properties were measured. As a result, retracted collaboration networks show more hierarchical and centralized structures, with strong correlations between degree and centrality measures, whereas non-retracted collaboration network metrics emphasize distributed collaboration with strong clustering and connectivity, indicating more balanced network structures compared to retracted metrics. The comparison between retracted and non-retracted collaboration networks highlights structural and functional overlaps. This indicates consistency in clustering and centrality across retracted and non-retracted networks, but highlights differences in weighted connections and assortative mixing. For statistical validation among the network metrics, a t-test is used to determine whether there is a statistically significant difference between the means of two groups. Metrics such as Degree Centrality, Average Weighted Degree, and Closeness Centrality reveal significant structural differences between the networks. These results highlight which aspects of the network topology differ significantly, shedding light on how structural and dynamic properties can vary between the two contexts. Finally, Cohen’s d test is used after a t-test to quantify the effect size, pro

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hindi audio-video-Deepfake (HAV-DF): A Hindi language-based Audio-video Deepfake dataset

arXiv

引用

arXiv 2024年

作者： Kaur, Sukhandeep Buhari, Mubashir Khandelwal, Naman Tyagi, Priyansh Sharma, Kiran School of Engineering & Technology BML Munjal University Haryana Gurugram122413 India Center for Advanced Data and Computational Science BML Munjal University Haryana Gurugram122413 India

Deepfakes, while technologically impressive, present a dual-edged sword. On the one hand, they have potential for innovation and creativity. However, their misuse poses significant risks to privacy, trust, and security, making it essential to develop detection tools and ethical frameworks to mitigate harm. With a vast Hindi-speaking population, India is particularly vulnerable to deepfake-driven misinformation campaigns. Fake videos or speeches in Hindi can have an enormous impact on rural and semi-urban communities, where digital literacy tends to be lower and people are more inclined to trust video content. The development of effective frameworks and detection tools to combat deepfake misuse requires high-quality, diverse, and extensive datasets. The existing popular datasets like FF-DF (FaceForensics++), and DFDC (DeepFake Detection Challenge) are based on English language, and there is a lack of regional language datasets. Hence, the aim of this paper is to create a first novel Hindi deep fake dataset, named "Hindi audio-video-Deepfake" (HAV-DF). The dataset has been generated using the faceswap, lipsyn and voice cloning methods. This multistep process allows us to create a rich, varied dataset that captures the nuances of Hindi speech and facial expressions, providing a robust foundation for training and evaluating deepfake detection models in a Hindi language context. It is unique of its kind as all of the previous datasets contain either deepfake videos or synthesized audio. This type of deepfake dataset can be used for training a detector for both deepfake video and audio datasets. Notably, the newly introduced HAV-DF dataset demonstrates lower detection accuracy’s across existing detection methods like Headpose, Xception-c40 Mesonet, etc. Compared to other well-known datasets FF-DF (FaceForensics++), and DFDC (DeepFake Detection Challenge). This trend suggests that the HAV-DF dataset presents deeper challenges to detect, possibly due to its focus on Hindi l

关键词： Temperature sensors

来源：评论

学校读者我要写书评

暂无评论

The OsWRKY72-OsAAT30/OsGSTU26 module mediates reactive oxygen species scavenging to drive heterosis for salt tolerance in hybrid rice

引用

Journal of Integrative Plant Biology 2024年第4期66卷 709-730页

作者： Citao Liu Bigang Mao Yanxia Zhang Lei tian Biao Ma Zhuo Chen Zhongwei Wei Aifu Li Ye Shao Gongye Cheng Lingling Li Wenyu Li Di Zhang Xiaoping Ding Jiangxiang Peng Yulin Peng Jiwai He Nenghui Ye Dingyang Yuan Chengcai Chu Meijuan Duan Hunan Provincial Key Laboratory of Stress Biology College of AgricultureHunan Agricultural UniversityChangsha 410128China State Key Laboratory of Hybrid Rice Hunan Hybrid Rice Research CenterChangsha 410125China College of Agriculture South China Agricultural UniversityGuangzhou 510642China State Key Laboratory of Wheat and Maize Crop Science Center for Crop Genome EngineeringCollege of AgronomyHenan Agricultural UniversityZhengzhou 450002China College of Horticulture Fujian Agriculture and Forestry UniversityFuzhou 350002China Department of Computational Medicine and Bioinformatics University of MichiganAnn ArborMI 48109 USA Biobin Data Science Co. Ltd.Changsha 410221China

Hybrid rice(Oryza sativa)generally outperforms its inbred parents in yield and stress tolerance,a phenomenon termed heterosis,but the underlying mechanism is not completely ***,we combined transcriptome,proteome,physiological,and heterosis analyses to examine the salt response of super hybrid rice Chaoyou1000(CY1000).In addition to surpassing the mean values for its two parents(mid-parent heterosis),CY1000 exhibited a higher reactive oxygen species scavenging ability than both its parents(over-parent heterosis or heterobeltiosis).Nonadditive expression and allele-specific gene expression assays showed that the glutathione S-transferase gene OsGSTU26 and the amino acid transporter gene OsAAT30 may have major roles in heterosis for salt tolerance,acting in an overdominant fashion in ***,we identified OsWRKY72 as a common transcription factor that binds and regulates OsGSTU26 and *** salt-sensitive phenotypes were associated with the OsWRKY72^(paternal)genotype or the OsAAT30^(maternal)genotype in core rice germplasm ***72^(paternal)specifically repressed the expression of OsGSTU26 under salt stress,leading to salinity sensitivity,while OsWRKY72^(maternal)specifically repressed OsAAT30,resulting in salinity *** results suggest that the OsWRKY72-OsAAT30/OsGSTU26 module may play an important role in heterosis for salt tolerance in an overdominant fashion in CY1000 hybrid rice,providing valuable clues to elucidate the mechanism of heterosis for salinity tolerance in hybrid rice.

关键词： allele-specific gene expression(ASE) heterosis hybrid rice nonadditive effect(NAE) salt tolerance transcriptome and proteome

来源：评论

学校读者我要写书评

暂无评论

Experimental verification of an online traction parameter identification method

arXiv

引用

arXiv 2023年

作者： Kobelski, Alexander Osinenko, Pavel Streif, Stefan Technische Universität Chemnitz Automatic Control and System Dynamics Laboratory Germany Skolkovo Institute of Science and Technology Computational and Data Science and Engineering Center Moscow Russia

Traction parameters, that characterize the ground-wheel contact dynamics, are the central factor in the energy efficiency of vehicles. To optimize fuel consumption, reduce wear of tires, increase productivity etc., knowledge of current traction parameters is unavoidable. Unfortunately, these parameters are difficult to measure and require expensive force and torque sensors. An alternative way is to use system identification to determine them. In this work, we validate such a method in field experiments with a mobile robot. The method is based on an adaptive Kalman filter. We show how it estimates the traction parameters online, during the motion on the field, and compare them to their values determined via a 6-directional force-torque sensor installed for verification. data of adhesion slip ratio curves is recorded and compared to curves from literature for additional validation of the method. The results can establish a foundation for a number of optimal traction methods. © 2023, CC BY-NC-ND.

关键词： Parameter estimation

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：