检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lyu, Aobo Clark, Andrew Raviv, Netanel Department of Electrical and Systems Engineering Washington University in St. Louis St. LouisMO United States Department of Computer Science and Engineering Washington University in St. Louis St. LouisMO United States

Mutual information between two random variables is a well-studied notion, whose understanding is fairly complete. Mutual information between one random variable and a pair of other random variables, however, is a far more involved notion. Specifically, Shannon’s mutual information does not capture fine-grained interactions between those three variables, resulting in limited insights in complex systems. To capture these fine-grained interactions, in 2010 Williams and Beer proposed to decompose this mutual information to information atoms, called unique, redundant, and synergistic, and proposed several operational axioms that these atoms must satisfy. In spite of numerous efforts, a general formula which satisfies these axioms has yet to be found. Inspired by Judea Pearl’s do-calculus, we resolve this open problem by introducing the do-operation, an operation over the variable system which sets a certain marginal to a desired value, which is distinct from any existing approaches. Using this operation, we provide the first explicit formula for calculating the information atoms so that Williams and Beer’s axioms are satisfied, as well as additional properties from subsequent studies in the field. Copyright © 2024, The Authors. All rights reserved.

关键词： Random variables

来源：评论

学校读者我要写书评

暂无评论

OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality

arXiv

引用

arXiv 2024年

作者： Fan, Chao Hou, Saihui Liang, Junhao Shen, Chuanfu Ma, Jingzhe Jin, Dongyang Huang, Yongzhen Yu, Shiqi The Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China The Department of Industrial and Manufacturing Systems Engineering University of Hong Kong Hong Kong The School of Artificial Intelligence Beijing Normal University China Watrix Technology Limited Co. Ltd Beijing China

Gait recognition, a rapidly advancing vision technology for person identification from a distance, has made significant strides in indoor settings. However, evidence suggests that existing methods often yield unsatisfactory results when applied to newly released real-world gait datasets. Furthermore, conclusions drawn from indoor gait datasets may not easily generalize to outdoor ones. Therefore, the primary goal of this work is to present a comprehensive benchmark study aimed at improving practicality rather than solely focusing on enhancing performance. To this end, we first develop OpenGait, a flexible and efficient gait recognition platform. Using OpenGait as a foundation, we conduct in-depth ablation experiments to revisit recent developments in gait recognition. Surprisingly, we detect some imperfect parts of certain prior methods thereby resulting in several critical yet undiscovered insights. Inspired by these findings, we develop three structurally simple yet empirically powerful and practically robust baseline models, i.e., DeepGaitV2, SkeletonGait, and SkeletonGait++, respectively representing the appearance-based, model-based, and multi-modal methodology for gait pattern description. Beyond achieving SoTA performances, more importantly, our careful exploration sheds new light on the modeling experience of deep gait models, the representational capacity of typical gait modalities, and so on. We hope this work can inspire further research and application of gait recognition towards better practicality. The code is available at https://***/ShiqiYu/OpenGait. © 2024, CC BY-NC-ND.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Multilayer perceptron ensembles in a truly sparse training context

引用

Neural Computing and Applications 2025年

作者： van der Wal, Peter R. D. Strisciuglio, Nicola Azzopardi, George Mocanu, Decebal Constatin Information Systems Group Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh 9 Groningen9747 AG Netherlands Data Management and Biometrics Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Hallenweg 19 Enschede7522 NH Netherlands Department of Computer Science Faculty of Science Technology and Medicine University of Luxembourg Maison du Nombre 6 avenue de la Fonte Esch4364 Luxembourg

Ensemble learning for artificial neural networks (ANNs) is an effective method to enhance predictive performance. However, ANNs are computationally and memory intensive, and naively training multiple networks can lead to excessive training times and costs. An effective tool for improving ensemble efficiency is introducing topological sparsity. Even though several implementations of efficient ensembles have been proposed, none of them can provide actual benefits in terms of computational overhead as the sparsity is simulated using binary masks. In this paper, we address this issue by introducing a Truly Sparse Ensemble without binary masks and directly incorporate native sparsity. We also propose two algorithms for initializing new subnetworks within the ensemble, leveraging this native topological sparsity to enhance subnetwork diversity. We demonstrate the performance of the resulting models at high levels of sparsity on several datasets in terms of classification accuracy, floating point operations (FLOPs), and actual running time. The proposed methods outperform all baseline dense and truly sparse models on tabular data, successfully diversify the training trajectory of the subnetworks, and increase the topological distance between subnetworks after re-initialization. © The Author(s) 2025.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation for Semantic Segmentation of Cataract Surgical Images Based on Masked Image Consistency 2nd

Domain Adaptation for Semantic Segmentation of Cataract Surg...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Zhang, Yuzhu Pan, Yijie Ou, Mingyang Gong, Guanghui Zhang, Qinhu Li, Haojin Li, Heng Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Ningbo China Eastern Institute for Advanced Study Eastern Institute of Technology Ningbo China

ISBN: (纸本)9789819619061

Cataract surgery is a complex procedure requiring precise execution of multiple steps. To improve the accuracy and efficiency of cataract surgeries, we present a semantic segmentation model for cataract surgery scenes. Our model leverages Unsupervised Domain Adaptation (UDA) techniques to enhance segmentation performance in clinical surgical environments, addressing challenges such as domain shift, occlusions between surgical tools and tissues, and long tail problem. The model utilizes a Teacher-Student model, where a student model is trained in the target domain with pseudo-labels generated by an Exponential Moving Average (EMA) teacher model, ensuring robust learning across domains. Additionally, we utilize a Masked Image Consistency (MIC) module to improve the model’s understanding of occluded regions by enforcing consistency between masked and unmasked predictions. To mitigate class imbalance between anatomical structures and surgical tools, we employ a maximum squares loss, enabling the model to achieve balanced learning. Our results demonstrate that the proposed model improves segmentation accuracy and robustness in cataract surgery scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement

Distributed Optimization with Finite Bit Adaptive Quantizati...

引用

IEEE Conference on Decision and Control

作者： Apostolos I. Rikos Wei Jiang Themistoklis Charalambous Karl H. Johansson Artificial Intelligence Thrust of the Information Hub The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong China Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia Cyprus Division of Decision and Control Systems KTH Royal Institute of Technology SE-100 44 Stockholm Sweden

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In realistic distributed optimization scenarios, individual nodes possess only partial information and communicate over bandwidth constrained channels. For this reason, the development of efficient distributed algorithms is essential. In our paper we addresses the challenge of unconstrained distributed optimization. In our scenario each node’s local function exhibits strong convexity with Lipschitz continuous gradients. The exchange of information between nodes occurs through 3-bit bandwidth-limited channels (i.e., nodes exchange messages represented by a only 3 -bits). Our proposed algorithm respects the network’s bandwidth constraints by leveraging zoom-in and zoom-out operations to adjust quantizer parameters dynamically. We show that during our algorithm’s operation nodes are able to converge to the exact optimal solution. Furthermore, we show that our algorithm achieves a linear convergence rate to the optimal solution. We conclude the paper with simulations that highlight our algorithm’s unique characteristics.

关键词： Adaptation models Quantization (signal) Heuristic algorithms Bandwidth Distributed algorithms Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Cross-Cultural Insights in Health: Integrating Machine Learning and Deep Learning for Early Predictive Diabetes Detection

Cross-Cultural Insights in Health: Integrating Machine Learn...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Tonmoy Roy H.M. Nahid Kawsar Iffat Rimi Md. Zehan Alam Department of Data Analytics and Information Systems Utah State University Logan Utah USA Department of Applied Mathematics Noakhali Science and Technology University Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Mathematics University of Dhaka Dhaka Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Diabetes, a potentially life-threatening condition if undetected, necessitates an early and accurate diagnosis. This study evaluates traditional machine learning (ML) models and deep neural networks (DNNs) for diabetes prediction, utilizing the Pima Indians Diabetes Dataset (PIDD) and the Sylhet Diabetes Hospital dataset (SDHD). We optimized six ML models—Logistic Regression, Decision Trees, Random Forests, Gradient Boosting, Support Vector Machines, and K-Nearest Neighbors—using GridSearchCV and ensemble learning, and deployed DNNs with varied train-test splits (90-10%, 80-20%, and 70-30%). Evaluations on accuracy, precision, recall, F1-score, and AUC-ROC highlighted RF’s outstanding performance after GridSearchCV on the SDHD with Accuracy: 98%, Precision: 100%, Recall: 96%, F1 Score: 98%, AUC: 100% and on PIDD with Accuracy: 76%, Precision: 63%, Recall: 80%, F1 Score:70%, AUC:81%. This underscores advanced ML’s effectiveness in handling complex datasets and enhancing early diabetes detection strategies.

关键词： Support vector machines Accuracy Hospitals Artificial neural networks Predictive models Prediction algorithms Diabetes Ensemble learning Regression tree analysis Random forests

来源：评论

学校读者我要写书评

暂无评论

Optimized Energy-Efficient Hybrid LW-AES and LW-ECC Security Framework for VLC and RF Networks

Optimized Energy-Efficient Hybrid LW-AES and LW-ECC Security...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Venkatesan C Thamaraimanalan T Sathiya T Ranjithkumar M Radha K Shanmuga Priya K Department of Electronics and Communication Engineering HKBK College of Engineering Bengaluru Karnataka India Department of Electronics and Communication Engineering Sri Eshwar College of Engineering Coimbatore Tamilnadu India Department of Computer Science and Engineering Sona College of Technology Salem Tamilnadu India Department of Computer Science and Business Systems Knowledge Institute of Technology Salem Tamilnadu India Department of AI & DS Vivekananda College of Technology for Women Thiruchengode Tamilnadu India Department of Cyber Scurity K.S.R College of Engineering Thiruchengode Tamilnadu India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

In hybrid Visible Light Communication (VLC) and Radio Frequency (RF) networks, optimizing energy efficiency and ensuring secure resource allocation are key challenges. This paper addresses these issues by introducing a Hybrid Lightweight Advanced Encryption Standard (LW-AES) and Lightweight Elliptic Curve Cryptography (LW-ECC) secure resource algorithm. This innovative approach aims to enhance the sustainability and reliability of communication systems across diverse environments. Our analysis reveals substantial performance improvements compared to existing methods, including higher throughput (100 Mbps) and packet delivery ratio (98%), with reduced latency (10 ms) and extended network lifetime (500 hours). The algorithm also features lower memory usage (100 KB) and enhanced energy efficiency, showing a 20% decrease in energy consumption (800 mW) and an energy efficiency of 0.8 mJ/bit. Security is bolstered with a 25% reduction in interception probability (3.75%) and a 50% increase in secure communication range (150 meters). Moreover, the approach aligns with green communication objectives, reducing CO2 emissions by 20% (800 kg/year) and achieving an energy efficiency metric of 10 nJ/bit. Communication safety is markedly improved, with an 80% decrease in outage probability (1%) and a 40% boost in reliability (84%). By integrating LW-AES and LW-ECC in a hybrid configuration, this research offers a robust framework for advancing sustainable and resilient hybrid VLC-RF networks, effectively meeting the evolving needs of modern communication systems.

关键词： Radio frequency Communication systems Memory management Throughput Energy efficiency Safety Security Resource management Reliability Visible light communication

来源：评论

学校读者我要写书评

暂无评论

Shoulder Surfing Resistant Graphical Password Schema: Randomized Pass Points (RPP) 14

Shoulder Surfing Resistant Graphical Password Schema: Random...

引用

14th International Conference on Information Security and Cryptology, ISCTURKEY 2021

作者： Bostan, Hakan Bostan, Atila Middle East Technical University Computer Engineering Department Ankara Turkey Ankara Science University Management Information Systems Ankara Turkey

ISBN: (纸本)9781665407762

In this study, a pass-graph methodology that benefits from randomity and alternative pass-graphs derivation is proposed with the name of Randomized Pass Points. The proposed authentication methodology is scrutinized for its resistance against brute force and shoulder-surfing attacks. Evaluations prove that the proposed alternative is stronger than that of 8-digit 71-character-set password methodology against brute force attacks and it necessitates at least 5 valid log-ins be captured by the attacker to derive the pass-graph under given assumptions in shoulder-surfing attack. © 2021 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

An Image Acquisition Scheme for Visual Odometry based on Image Bracketing and Online Attribute Control

An Image Acquisition Scheme for Visual Odometry based on Ima...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Shuyang Zhang Jinhao He Bohuan Xue Jin Wu Pengyu Yin Jianhao Jiao Ming Liu Department of Electronic and Computer Engineering the Hong Kong University of Science and Technology Hong Kong SAR China Thrust of Robotics and Autonomous Systems the Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Center for Advanced Robotics Technology Innovation (CARTIN) School of Electrical and Electronic Engineering Nanyang Technological University Singapore Department of Computer Science University College London London UK

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Visual odometry (VO) system is challenged by complex illumination environments. Image quality and its consistency in the time domain directly determine feature detection and tracking performance, which further affect the robustness and accuracy of the entire system. In this paper, an image acquisition scheme with image bracketing patterns is proposed. Images with different exposure levels are continuously captured to sufficiently explore the scene under varying illumination. An attribute control method is designed to adjust image exposures within the brackets online. Gaussian process regression fits the relationship between image quality metric and exposure via image synthesis technique. The optimal exposures for the next bracket are obtained directly without attempts to ensure a quick response. Experiments show our acquisition system’s effectiveness and performance improvement for VO tasks in complex illumination scenes.

关键词： Image quality Measurement Image synthesis Lighting Gaussian processes Robustness Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent

arXiv

引用

arXiv 2025年

作者： Fang, Cheng Dixit, Rishabh Bajwa, Waheed U. Gürbüzbalaban, Mert Department of Electrical and Computer Engineering Rutgers University New BrunswickNJ United States Department of Mathematics University of California San DiegoCA United States Departments of Electrical and Computer Engineering and Statistics Rutgers University New BrunswickNJ United States Departments of Electrical and Computer Engineering Management Science and Information Systems and Statistics Rutgers University New BrunswickNJ United States

Empirical risk minimization (ERM) is a cornerstone of modern machine learning (ML), supported by advances in optimization theory that ensure efficient solutions with provable algorithmic convergence rates, which measure the speed at which optimization algorithms approach a solution, and statistical learning rates, which characterize how well the solution generalizes to unseen data. Privacy, memory, computational, and communications constraints increasingly necessitate data collection, processing, and storage across network-connected devices. In many applications, these networks operate in decentralized settings where a central server cannot be assumed, requiring decentralized ML algorithms that are both efficient and resilient. Decentralized learning, however, faces significant challenges, including an increased attack surface for adversarial interference during decentralized learning processes. This paper focuses on the man-in-the-middle (MITM) attack, wherein adversaries exploit communication vulnerabilities between devices to inject malicious updates during training, potentially causing models to deviate significantly from their intended ERM solutions. To address this challenge, we propose RESIST (Resilient dEcentralized learning using conSensus gradIent deScenT), an optimization algorithm designed to be robust against adversarially compromised communication links, where transmitted information may be arbitrarily altered before being received. Unlike existing adversarially robust decentralized learning methods, which often (i) guarantee convergence only to a neighborhood of the solution, (ii) lack guarantees of linear convergence for strongly convex problems, or (iii) fail to ensure statistical consistency as sample sizes grow, RESIST overcomes all three limitations. It achieves algorithmic and statistical convergence for strongly convex, Polyak–Lojasiewicz, and nonconvex ERM problems by employing a multistep consensus gradient descent framework and robust statis

关键词： Adversarial machine learning

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：