检索结果-内蒙古大学图书馆

In-depth review of AI-enabled unmanned aerial vehicles: trends, vision, and challenges

Discover Artificial Intelligence 2024年第1期4卷 1-24页

作者： Pal, Osim Kumar Shovon, MD Sakib Hossain Mridha, M.F. Shin, Jungpil Department of Electrical & Computer Engineering University of Patras Rion-Patras Patras26504 Greece Department of Computer Science American International University-Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering The University of Aizu Aizu Aizuwakamatsu965-8580 Japan

In recent times, AI and UAV have progressed significantly in several applications. This article analyzes applications of UAV with modern green computing in various sectors. It addresses cutting-edge technologies such as green computing, generative AI, future scope, and related concerns in UAV. The research investigates the role of green computing and generative AI in combination with UAVs for navigation, object recognition and tracking, wildlife monitoring, precision agriculture, rescue operations, surveillance, and UAV communication. This study examines how modern computing technologies and UAVs are being applied in agriculture, surveillance, disaster management, and other areas. The ethics of UAV and AI applications, including safety, legal frameworks, and other issues, are thoroughly investigated. This research examines AI-based UAV applications across different disciplines, using open-source data and current advancements for future growth in this domain. This investigation will aid future researchers in their exploration of UAVs using cutting-edge computing technologies. © The Author(s) 2024.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Hybrid two-level protection system for preserving pre-trained DNN models ownership

引用

Neural Computing and Applications 2024年第34期36卷 21415-21449页

作者： Fkirin, Alaa Moursi, Ahmed Samy Attiya, Gamal El-Sayed, Ayman Shouman, Marwa A. Department of Electrical Engineering Faculty of Engineering Fayoum University Fayoum Egypt Computer Science and Engineering Department Faculty of Electronic Engineering Menoufia Governorate Menouf32952 Egypt

Recent advancements in deep neural networks (DNNs) have made them indispensable for numerous commercial applications. These include healthcare systems and self-driving cars. Training DNN models typically demands substantial time, vast datasets and high computational costs. However, these valuable models face significant risks. Attackers can steal and sell pre-trained DNN models for profit. Unauthorised sharing of these models poses a serious threat. Once sold, they can be easily copied and redistributed. Therefore, a well-built pre-trained DNN model is a valuable asset that requires protection. This paper introduces a robust hybrid two-level protection system for safeguarding the ownership of pre-trained DNN models. The first-level employs zero-bit watermarking. The second-level incorporates an adversarial attack as a watermark by using a perturbation technique to embed the watermark. The robustness of the proposed system is evaluated against seven types of attacks. These are Fast Gradient Method Attack, Auto Projected Gradient Descent Attack, Auto Conjugate Gradient Attack, Basic Iterative Method Attack, Momentum Iterative Method Attack, Square Attack and Auto Attack. The proposed two-level protection system withstands all seven attack types. It maintains accuracy and surpasses current state-of-the-art methods. © The Author(s) 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Consensus-relevance kNN and covariate shift mitigation

引用

MACHINE LEARNING 2024年第1期113卷 325-353页

作者： Kalpakis, Konstantinos Computer Science and Electrical Engineering Department University of Maryland Baltimore County 1000 Hilltop Circle Baltimore MD 21250 USA

Classification and regression algorithms based on k-nearest neighbors (kNN) are often ranked among the top-10 Machine learning algorithms, due to their performance, flexibility, interpretability, non-parametric nature, and computational efficiency. Nevertheless, in existing kNN algorithms, the kNN radius, which plays a major role in the quality of kNN estimates, is independent of any weights associated with the training samples in a kNN-neighborhood. This omission, besides limiting the performance and flexibility of kNN, causes difficulties in correcting for covariate shift (e.g., selection bias) in the training data, taking advantage of unlabeled data, domain adaptation and transfer learning. We propose a new weighted kNN algorithm that, given training samples, each associated with two weights, called consensus and relevance (which may depend on the query on hand as well), and a request for an estimate of the posterior at a query, works as follows. First, it determines the kNN neighborhood as the training samples within the kth relevance-weighted order statistic of the distances of the training samples from the query. Second, it uses the training samples in this neighborhood to produce the desired estimate of the posterior (output label or value) via consensus-weighted aggregation as in existing kNN rules. Furthermore, we show that kNN algorithms are affected by covariate shift, and that the commonly used sample reweighing technique does not correct covariate shift in existing kNN algorithms. We then show how to mitigate covariate shift in kNN decision rules by using instead our proposed consensus-relevance kNN algorithm with relevance weights determined by the amount of covariate shift (e.g., the ratio of sample probability densities before and after the shift). Finally, we provide experimental results, using 197 real datasets, demonstrating that the proposed approach is slightly better (in terms of F-1 score) on average than competing benchmark approaches for mit

关键词： Nearest neighbors Selection bias Covariate shift Density estimation kNN learners

来源：评论

学校读者我要写书评

暂无评论

Enhancing Renewable Energy Integration:A Gaussian-Bare-Bones Levy Cheetah Optimization Approach to Optimal Power Flow in electrical Networks

引用

computer Modeling in engineering & sciences 2024年第8期140卷 1339-1370页

作者： Ali S.Alghamdi Mohamed A.Zohdy Saad Aldoihi Department of Electrical Engineering College of EngineeringMajmaah UniversityAl-Majmaah11952Saudi Arabia Electrical and Computer Engineering Department Oakland UniversityRochesterMI48309USA Institute of Earth and Space Science King Abdulaziz City for Science and Technology(KACST)Riyadh11442Saudi Arabia Computer Science and Systems Engineering Institute Polytechnique de ParisPalaiseau CedexFrance

In the contemporary era,the global expansion of electrical grids is propelled by various renewable energy sources(RESs).Efficient integration of stochastic RESs and optimal power flow(OPF)management are critical for network *** study introduces an innovative solution,the Gaussian Bare-Bones Levy Cheetah Optimizer(GBBLCO),addressing OPF challenges in power generation systems with stochastic *** primary objective is to minimize the total operating costs of RESs,considering four functions:overall operating costs,voltage deviation management,emissions reduction,voltage stability index(VSI)and power loss ***,a carbon tax is included in the objective function to reduce carbon *** scrutiny,using modified IEEE 30-bus and IEEE 118-bus systems,validates GBBLCO’s superior performance in achieving optimal *** results demonstrate GBBLCO’s efficacy in six optimization scenarios:total cost with valve point effects,total cost with emission and carbon tax,total cost with prohibited operating zones,active power loss optimization,voltage deviation optimization and enhancing voltage stability index(VSI).GBBLCO outperforms conventional techniques in each scenario,showcasing rapid convergence and superior solution ***,GBBLCO navigates complexities introduced by valve point effects,adapts to environmental constraints,optimizes costs while considering prohibited operating zones,minimizes active power losses,and optimizes voltage deviation by enhancing the voltage stability index(VSI)*** research significantly contributes to advancing OPF,emphasizing GBBLCO’s improved global search capabilities and ability to address challenges related to local *** emerges as a versatile and robust optimization tool for diverse challenges in power systems,offering a promising solution for the evolving needs of renewable energy-integrated power grids.

关键词： Renewable energy integration optimal power flow stochastic renewable energy sources gaussian-bare-bones levy cheetah optimizer electrical network optimization carbon tax optimization

来源：评论

学校读者我要写书评

暂无评论

Correction to: Transfer learning and self-distillation for automated detection of schizophrenia using single-channel EEG and scalogram images (Physical and engineering sciences in Medicine, (2024), 10.1007/s13246-024-01420-1)

引用

Physical and engineering sciences in Medicine 2025年第1期48卷 19-20页

作者： Mostafavi, Mohammadreza Ko, Seok-Bum Shokouhi, Shahriar Baradaran Ayatollahi, Ahmad Department of Electrical Engineering Electronic Engineering Iran University of Science and Technology Tehran Iran Division of Biomedical Engineering Department of Electrical and Computer Engineering University of Saskatchewan Saskatoon Canada

In this article the legend of Fig. 6 was presented without a reference. The legend of Fig. 6 has been changed from "The general framework for knowledge distillation involving a teacher-student relationship" to "The generic teacher-student framework for knowledge distillation [33]." In Sharma et al.’s research, two results obtained from the "KNN with ten-fold cross-validation" and "KNN with leave-one-subject-out cross-validation (LOSOCV)" methods are reported as the final results. Unfortunately, we mistakenly attributed the accuracy of one method. While we correctly listed the name of the method used, which is KNN with ten-fold cross-validation, we inadvertently entered the precision of the KNN with leave-one-subject-out cross-validation (LOSOCV) method. Therefore, we updated our results table (Table 7). The correct Table 7 is shown below. (Table presented.) Comparison of the performance of the proposed method with existing methods Study Method Dataset Accuracy Sensitivity Specificity Shim et al. [38] SVM 34 SZ-34 healthy 88.24% – – Siuly et al. [7] EBT – EMD (Empirical Mode Decomposition) 49 SZ-32 healthy 89.59% 0.8976 0.8932 Phang et al. [39] Multi-domain connectome CNN 45 SZ-39 healthy 91.69% 0.9111 0.925 Jahmunah et al. [40] Non-linear features, decision-tree, neural network, SVM 14 SZ and 14 healthy 92.90% 0.9345 0.9224 Akbari et al. [41] Phase space dynamic & graphical features 14 SZ and 14 healthy 94.8% 0.943 0.952 Shalbaf et al. [20] ResNet-18-SVM 14 SZ and 14 healthy 94.84% 0.980 0.9239 Bagherzadeh et al. [42] DenseNet121 model 14 SZ and 14 healthy 96.26% 0.9548 0.9702 Sharma et al. [43] KNN with ten-fold 14 SZ and 14 healthy 99.21% 0.9942 0.9905 LOSOCV 97.20% 0.9649 0.9806 Proposed method CWT—Self distillation- VGG16 14 SZ and 14 healthy 97.81 0.970 0.986 The original article has been corrected. © Australasian College of Physical Scientists and Engineers in Medicine 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault-tolerant properties of scale-free linear protocols for synchronization of homogeneous multi-agent systems

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4194-4201页

作者： Stoorvogel, Anton A. Saberi, Ali Liu, Zhenwei University of Twente Department of Electrical Engineering Mathematics and Computer Science P.O. Box 217 Enschede Netherlands Washington State University School of Electrical Engineering and Computer Science PullmanWA99164 United States Northeastern University College of Information Science and Engineering Shenyang110819 China

Originally, protocols were designed for multi-agent systems (MAS) using information about the network which might not be available. Recently, there has been a focus on scale-free synchronization where the protocol is designed without any prior information about the network. As long as the network contains a directed spanning tree, a scale-free protocol guarantees that the network achieves synchronization. If there is no directed spanning tree then synchronization cannot be achieved. But what happens when these scale-free protocols are applied to such a network where the directed spanning tree no longer exists? This paper establishes that the network decomposes into a number of basic bicomponents which achieves synchronization among all nodes in this basic bicomponent. On the other hand, nodes which are not part of any basic bicomponent converge to a weighted average of the synchronized trajectories of the basic bicomponents. The weights are independent of the initial conditions and are independent of the designed protocol. © 1963-2012 IEEE.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

SUMIT: Secure Unicast and Multicast Communication in Internet of Mobile Things

SUMIT: Secure Unicast and Multicast Communication in Interne...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Reefat, Hasin Ishraq Ebrahimabadi, Mohammad Younis, Mohamed Alkanhal, Mona Karimi, Naghmeh Department of Computer Science and Electrical Engineering United States

ISBN: (纸本)9798350351255

An Internet of Mobile Things (IoMT) refers to an internetworked group of pervasive devices that coordinate their motion and task execution through frequent status and data exchange. An IoMT could be serving critical applications such as military reconnaissance, security surveillance, etc., and hence the authenticity, integrity and confidentiality of the transmitted data must be ensured. Yet, achieving the security goals is challenging due to the dynamic nature of the network topology, the constrained computational and communication resources, and the variety of packet traffic patterns among the nodes. This paper proposes an effective solution that leverages lightweight hardware primitives, specifically, Physical Unclonable Functions (PUFs), to support secure communication in the network. The employed PUFs are used to generate peer-to-peer encryption keys to protect the data traffic among nodes and to the command center, while coping with the dynamic change of the network topology. Our solution efficiently supports both unicast and multicast communications. The proposed solution is validated through analysis and prototype implementation on an FPGA. © 2024 IEEE.

关键词： Secure communication

来源：评论

学校读者我要写书评

暂无评论

Manifold Clustering Based Nonlinear Model Reduction with Application to Nonlinear Convection 63

Manifold Clustering Based Nonlinear Model Reduction with App...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Wu, T. Wilson, D. Djouadi, S.M. Department of Electrical Engineering and Computer Science United States

ISBN: (纸本)9798350316339

This paper proposes a new cluster method combined with Dynamic Mode Decomposition with Control (DMDc), and the Proper Orthogonal Decomposition (POD) to construct more accurate reduced order models. DMDc and POD are popular data-driven techniques that extract loworder models from high-dimensional complex dynamic systems. However, these methods are inherently linear, i.e., the data is assumed to belong to linear manifolds. However, this may lead to inaccuracies in the reduced models commensurate with the presence of nonlinearities. To capture the nonlinear behavior, manifold clustering is introduced to group the snapshots obtained by experiments or numerical simulation into several sub-regions based on the underlying non-linear structure. Manifold clustering is a powerful approach for exploratory data analysis, allowing the discovery of patterns and structures that are not apparent in raw high-dimensional data. It does not require knowing the number of clusters and the intrinsic manifold dimensions in advance. Manifold clustering is combined with DMDc and POD to construct the local reduced-order models. Time clustering is applied to the snapshots generated by a nonlinear convective flow governed by the 2D Burgers' equations with boundary actuation. The manifold cluster reduced order model outperforms standard and other cluster-based (K-means) reduced order models. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Noisy Computing of the Threshold Function 36

Noisy Computing of the Threshold Function

引用

36th International Conference on Algorithmic Learning Theory, ALT 2025

作者： Wang, Ziao Ghaddar, Nadim Zhu, Banghua Wang, Lele Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor United States Department of Electrical and Computer Engineering University of Toronto Canada Department of Electrical and Computer Engineering University of Washington United States Department of Electrical and Computer Engineering University of British Columbia Canada

Coping with noise in computing is an important problem to consider in large systems. With applications in fault tolerance (Hastad et al., 1987;Pease et al., 1980;Pippenger et al., 1991), noisy sorting (Shah and Wainwright, 2018;Agarwal et al., 2017;Falahatgar et al., 2017;Heckel et al., 2019;Wang et al., 2024a;Gu and Xu, 2023;Kunisky et al., 2024), noisy searching (Berlekamp, 1964;Horstein, 1963;Burnashev and Zigangirov, 1974;Pelc, 1989;Karp and Kleinberg, 2007), among many others, the goal is to devise algorithms with the minimum number of queries that are robust enough to detect and correct the errors that can happen during the computation. In this work, we consider the noisy computing of the threshold-k function. For n Boolean variables x = (x1, ..., xn) ∈ {0, 1}n, the threshold-k function THk(·) computes whether the number of 1's in x is at least k or not, i.e., (Equation presented) The noisy queries correspond to noisy readings of the bits, where at each time step, the agent queries one of the bits, and with probability p, the wrong value of the bit is returned. It is assumed that the constant p ∈ (0, 1/2) is known to the agent. Our goal is to characterize the optimal query complexity for computing the THk function with error probability at most δ. This model for noisy computation of the THk function has been studied by Feige et al. (1994), where the order of the optimal query complexity is established;however, the exact tight characterization of the optimal number of queries is still open. In this paper, our main contribution is tightening this gap by providing new upper and lower bounds for the computation of the THk function, which simultaneously improve the existing upper and lower bounds. The main result of this paper can be stated as follows: for any 1 ≤ k ≤ n, there exists an algorithm that computes the THk function with an error probability at most δ = o(1), and the algorithm uses at most (Equation presented) queries in expectation. Here we define m (Eq

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Frequency-Domain Pruning Algorithms for Accelerating Human Activity Recognition Tasks Based on Sensor Data

引用

computers, Materials & Continua 2024年第11期81卷 2219-2242页

作者： Jian Su Haijian Shao Xing Deng Yingtao Jiang School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas VegasNV 89154USA

The rapidly advancing Convolutional Neural Networks(CNNs)have brought about a paradigm shift in various computer vision tasks,while also garnering increasing interest and application in sensor-based Human Activity Recognition(HAR)***,the significant computational demands and memory requirements hinder the practical deployment of deep networks in resource-constrained *** paper introduces a novel network pruning method based on the energy spectral density of data in the frequency domain,which reduces the model’s depth and accelerates activity *** traditional pruning methods that focus on the spatial domain and the importance of filters,this method converts sensor data,such as HAR data,to the frequency domain for *** emphasizes the low-frequency components by calculating their energy spectral density ***,filters that meet the predefined thresholds are retained,and redundant filters are removed,leading to a significant reduction in model size without compromising performance or incurring additional computational ***,the proposed algorithm’s effectiveness is empirically validated on a standard five-layer CNNs backbone *** computational feasibility and data sensitivity of the proposed scheme are thoroughly ***,the classification accuracy on three benchmark HAR datasets UCI-HAR,WISDM,and PAMAP2 reaches 96.20%,98.40%,and 92.38%,***,our strategy achieves a reduction in Floating Point Operations(FLOPs)by 90.73%,93.70%,and 90.74%,respectively,along with a corresponding decrease in memory consumption by 90.53%,93.43%,and 90.05%.

关键词： Convolutional neural networks human activity recognition network pruning frequency-domain transformation

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：