检索结果-内蒙古大学图书馆

Artificial intelligence in physiological characteristics recognition for internet of things authentication

Digital Communications and Networks 2024年第3期10卷 740-755页

作者： Zhimin Zhang Huansheng Ning Fadi Farha Jianguo Ding Kim-Kwang Raymond Choo School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing100083China Faculty of Informatics Engineering Aleppo UniversityAleppoSyria Department of Computer Science Blekinge Institute of Technology37179KarlskronaSweden Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Effective user authentication is key to ensuring equipment security,data privacy,and personalized services in Internet of Things(IoT)***,conventional mode-based authentication methods(e.g.,passwords and smart cards)may be vulnerable to a broad range of attacks(e.g.,eavesdropping and side-channel attacks).Hence,there have been attempts to design biometric-based authentication solutions,which rely on physiological and behavioral *** characteristics need continuous monitoring and specific environmental settings,which can be challenging to implement in ***,we can also leverage Artificial Intelligence(AI)in the extraction and classification of physiological characteristics from IoT devices processing to facilitate ***,we review the literature on the use of AI in physiological characteristics recognition pub-lished after *** use the three-layer architecture of the IoT(i.e.,sensing layer,feature layer,and algorithm layer)to guide the discussion of existing approaches and their *** also identify a number of future research opportunities,which will hopefully guide the design of next generation solutions.

关键词： Physiological characteristics recognition Artificial intelligence Internet of things Biological-driven authentication

来源：评论

学校读者我要写书评

暂无评论

OUT-OF-DOMAIN UNLABELED DATA IMPROVES GENERALIZATION 12

OUT-OF-DOMAIN UNLABELED DATA IMPROVES GENERALIZATION

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Saberi, Amir Hossein Movasaghinia, Mohammad Hosein Najafi, Amir Motahari, Seyed Abolfazl Heidari, Alireza Khalaj, Babak H. Department of Electrical Engineering Department of Computer Engineering Sharif Center for Information Systems and Data Science Iran Sharif Institute for Convergence Science & Technology Sharif University of Technology Tehran Iran

We propose a novel framework for incorporating unlabeled data into semi-supervised classification problems, where scenarios involving the minimization of either i) adversarially robust or ii) non-robust loss functions have been considered. Notably, we allow the unlabeled samples to deviate slightly (in total variation sense) from the in-domain distribution. The core idea behind our framework is to combine Distributionally Robust Optimization (DRO) with self-supervised training. As a result, we also leverage efficient polynomial-time algorithms for the training stage. From a theoretical standpoint, we apply our framework on the classification problem of a mixture of two Gaussians in Rd, where in addition to the m independent and labeled samples from the true distribution, a set of n (usually with n m) out of domain and unlabeled samples are given as well. Using only the labeled data, it is known that the generalization error can be bounded by ∝ (d/m)1/2. However, using our method on both isotropic and non-isotropic Gaussian mixture models, one can derive a new set of analytically explicit and non-asymptotic bounds which show substantial improvement on the generalization error compared to ERM. Our results underscore two significant insights: 1) out-of-domain samples, even when unlabeled, can be harnessed to narrow the generalization gap, provided that the true data distribution adheres to a form of the "cluster assumption", and 2) the semi-supervised learning paradigm can be regarded as a special case of our framework when there are no distributional shifts. We validate our claims through experiments conducted on a variety of synthetic and real-world datasets. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

A Single DC Link Four Level Multilevel Inverter with Increased DC Bus Utilization for Drives 50

A Single DC Link Four Level Multilevel Inverter with Increas...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Pottekkat, Rohith Vivek, R.S. Gopakumar, K. Umanand, L. Subba Reddy, B. Franquelo, Leopoldo G. Interdisciplinary Centre for Energy Research Indian Institute of Science Bangalore India Department of Electrical Engineering College of Engineering Trivandrum Thiruvananathapuram India Department of Electronic Systems Engineering Indian Institute of Science Bangalore India

ISBN: (纸本)9781665464543

The paper proposes a low switch count multilevel inverter topology having a four-level space vector structure. The proposed MLI demonstrates a reduced number of active switches in relation to the number of output voltage levels. This inverter has an increased DC bus utilization, reaching up to 0.637 times the DC link voltage compared to the conventional multilevel inverters limited to 0.577 times the DC link voltage. The proposed multilevel inverter configuration integrates a two-level inverter with a cascaded H-bridge (CHB) converter in each phase. The each CHB capacitor voltage are regulated to one third of dc link voltage. The enhanced utilization of the DC bus voltage is due to the space vector redundancies provided by the CHB units. Both simulation and experimental validation of the proposed scheme are conducted on an induction motor drive across for various operating conditions. Field-oriented control (FOC) is employed to control the speed of the induction machine, while examining capacitor balancing under various transient conditions. © 2024 IEEE.

关键词： Induction motors

来源：评论

学校读者我要写书评

暂无评论

The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations 38

The Group Robustness is in the Details: Revisiting Finetunin...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： LaBonte, Tyler Hill, John C. Zhang, Xinchen Muthukumar, Vidya Kumar, Abhishek H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Google DeepMind United Kingdom

Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper, we identify surprising and nuanced behavior of finetuned models on worst-group accuracy via comprehensive experiments on four well-established benchmarks across vision and language tasks. We first show that the commonly used class-balancing techniques of mini-batch upsampling and loss upweighting can induce a decrease in worst-group accuracy (WGA) with training epochs, leading to performance no better than without class-balancing. While in some scenarios, removing data to create a class-balanced subset is more effective, we show this depends on group structure and propose a mixture method which can outperform both techniques. Next, we show that scaling pretrained models is generally beneficial for worst-group accuracy, but only in conjunction with appropriate class-balancing. Finally, we identify spectral imbalance in finetuning features as a potential source of group disparities - minority group covariance matrices incur a larger spectral norm than majority groups once conditioned on the classes. Our results show more nuanced interactions of modern finetuned models with group robustness than was previously known. Our code is available at https://***/tmlabonte/revisiting-finetuning. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single Photon LiDAR Compression: An Overview 66

Single Photon LiDAR Compression: An Overview

引用

2023 IEEE 66th International Midwest Symposium on Circuits and systems, MWSCAS 2023

作者： Al-Shabili, Abdullah H Weerasooriya, Hashan K Weligampola, Harshana Chennuri, Prateek Abshire, Pamela Chan, Stanley School of Electrical and Computer Engineering Purdue University West LafayetteIN United States University of Maryland Department of Electrical and Computer Engineering Institute of System Research College ParkMD United States

ISBN: (纸本)9798350302103

Real-time mapping of the surroundings plays a pivotal role in ensuring the success of autonomous vehicles. Among the technologies showing promise for depth mapping is Single Photon Light Detection and Ranging (SPL) which offers impressive long-range capabilities, superior depth resolution, and energy-efficient laser sources. However, the adoption of high-resolution, high frame-rate SPL systems results in significant data volumes, often reaching several Gbit/s. This creates a throughput bottleneck that impedes real-time applications and necessitates the development of effective compression schemes. This paper addresses the challenges associated with SPL compression and provides a comprehensive overview of recent advancements in this domain. The review encompasses various compression methods, including algorithmic and/or hardware-based approaches, spatial and/or temporal compression techniques. We also discuss future directions, such as integrating deep learning and fusion techniques with other sensing modalities. © 2023 IEEE.

关键词： compression compressive learning compressive sensing deep learning depth imaging Single Photon LiDAR (SPL)

来源：评论

学校读者我要写书评

暂无评论

Non-cooperative target pose estimation based on improved iterative closest point algorithm

引用

Journal of systems engineering and Electronics 2022年第1期33卷 1-10页

作者： ZHU Zijian XIANG Wenhao HUO Ju YANG Ming ZHANG Guiyang WEI Liang Department of Astronautics Harbin Institute of TechnologyHarbin 150006China Department of Electrical Engineering and Automation Harbin Institute of TechnologyHarbin 150006China Systems Engineering Research Institute China State Shipbuilding Corporation LimitedBeijing 100036China

For localisation of unknown non-cooperative targets in space,the existence of interference points causes inaccuracy of pose estimation while utilizing point cloud *** address this issue,this paper proposes a new iterative closest point(ICP)algorithm combined with distributed weights to intensify the dependability and robustness of the non-cooperative target *** interference points in space have not yet been extensively studied,we classify them into two broad categories,far interference points and near interference *** the former,the statistical outlier elimination algorithm is *** the latter,the Gaussian distributed weights,simultaneously valuing with the variation of the Euclidean distance from each point to the centroid,are commingled to the traditional ICP *** each iteration,the weight matrix W in connection with the overall localisation is obtained,and the singular value decomposition is adopted to accomplish high-precision estimation of the target ***,the experiments are implemented by shooting the satellite model and setting the position of interference *** outcomes suggest that the proposed algorithm can effectively suppress interference points and enhance the accuracy of non-cooperative target pose *** the interference point number reaches about 700,the average error of angle is superior to 0.88°.

关键词： non-cooperative target pose estimation iterative closest point(ICP) Gaussian weight

来源：评论

学校读者我要写书评

暂无评论

Collaborative Manipulation of Deformable Objects with Predictive Obstacle Avoidance

Collaborative Manipulation of Deformable Objects with Predic...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Burak Aksoy John T. Wen Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Manipulating deformable objects arises in daily life and numerous applications. Despite phenomenal advances in industrial robotics, manipulation of deformable objects remains mostly a manual task. This is because of the high number of internal degrees of freedom and the complexity of predicting its motion. In this paper, we apply the computationally efficient position-based dynamics method to predict object motion and distance to obstacles. This distance is incorporated in a control barrier function for the resolved motion kinematic control for one or more robots to adjust their motion to avoid colliding with the obstacles. The controller has been applied in simulations to 1D and 2D deformable objects with varying numbers of assistant agents, demonstrating its versatility across different object types and multi-agent systems. Results indicate the feasibility of real-time collision avoidance through deformable object simulation, minimizing path tracking error while maintaining a predefined minimum distance from obstacles and preventing overstretching of the deformable object. The implementation is performed in ROS, allowing ready portability to different applications.

关键词： Deformable models Service robots Tracking Collaboration Manuals Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

The good, the bad and the ugly sides of data augmentation: an implicit spectral regularization perspective

The Journal of Machine Learning Research

引用

The Journal of Machine Learning research 2024年第1期25卷 4470-4554页

作者： Chi-Heng Lin Chiraag Kaushik Eva L. Dyer Vidya Muthukumar School of Electrical & Computer Engineering Georgia Institute of Technology Atlanta GA Coulter Department of Biomedical Engineering School of Electrical & Computer Engineering Georgia Institute of Technology Atlanta GA School of Electrical & Computer Engineering School of Industrial & Systems Engineering Georgia Institute of Technology Atlanta GA

Data augmentation (DA) is a powerful workhorse for bolstering performance in modern machine learning. Specific augmentations like translations and scaling in computer vision are traditionally believed to improve generalization by generating new (artificial) data from the same distribution. However, this traditional viewpoint does not explain the success of prevalent augmentations in modern machine learning (e.g. randomized masking, cutout, mixup), that greatly alter the training data distribution. In this work, we develop a new theoretical framework to characterize the impact of a general class of DA on underparameterized and overparameterized linear model generalization. Our framework reveals that DA induces implicit spectral regularization through a combination of two distinct effects: a) manipulating the relative proportion of eigenvalues of the data covariance matrix in a training-data-dependent manner, and b) uniformly boosting the entire spectrum of the data covariance matrix through ridge regression. These effects, when applied to popular augmentations, give rise to a wide variety of phenomena, including discrepancies in generalization between over-parameterized and under-parameterized regimes and differences between regression and classification tasks. Our framework highlights the nuanced and sometimes surprising impacts of DA on generalization, and serves as a testbed for novel augmentation design.

关键词： data augmentation generalization analysis overparameterized models spectral analysis regression classification

来源：评论

学校读者我要写书评

暂无评论

Corrections to "Reed Solomon Codes Against Adversarial Insertions and Deletions"

引用

IEEE Transactions on Information Theory 2025年第4期71卷 3237-3238页

作者： Con, Roni Shpilka, Amir Tamo, Itzhak Technion – Israel Institute of Technology Department of Computer Science Haifa3200003 Israel Tel Aviv University Blavatnik School of Computer Science Tel Aviv6997801 Israel Tel Aviv University Department of Electrical Engineering-Systems Tel Aviv6997801 Israel

The purpose of this note is to correct an error made by Con et al. (2023), specifically in the proof of Theorem 9. Here we correct the proof but as a consequence we get a slightly weaker result. In Theorem9, we claimed that for integers k and n such that k q RS code that can decode from n - 2k + 1 insdel errors where (Formula presented). Here we prove the following. Theorem 1: For integers n and k q RS-code, where (Formula presented) is a prime power, that can decode from n - 2k + 1 adversarial insdel errors. Note that the exponent of n is 4k - 3 whereas in Theorem 9 it is 4k - 4. For constant dimensional codes, the field size is of order O(n4k-3) , and in particular, for k = 2 the field size is of order O(n5) . © 1963-2012 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards new realities: Implications of personalized online layers in our daily lives

引用

i-com 2024年第2期23卷 221-229页

作者： Herder, Eelco Stojko, Laura Strecker, Jannis Neumayr, Thomas Yigitbas, Enes Augstein, Mirjam Department of Information and Computing Sciences Utrecht University Utrecht Netherlands Department of Computer Science University of the Bundeswehr Munich Neubiberg Germany Institute of Computer Science University of St. Gallen St. Gallen Switzerland Research Group Personalized Environments and Collaborative Systems University of Applied Sciences Upper Austria Hagenberg Austria Faculty of Electrical Engineering Computer Science and Mathematics Paderborn University Paderborn Germany

We are currently in a period of upheaval, as many new technologies are emerging that open up new possibilities to shape our everyday lives. Particularly, within the field of Personalized Human-computer Interaction we observe high potential, but also challenges. In this article, we explore how an increasing amount of online services and tools not only further facilitates our lives, but also shapes our lives and how we perceive our environments. For this purpose, we adopt the metaphor of personalized 'online layers' and show how these layers are and will be interwoven with the lives that we live in the 'human layer' of the real world. © 2024 the author(s), published by De Gruyter, Berlin/Boston.

关键词： Human computer interaction

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：