检索结果-内蒙古大学图书馆

Overview of Task Offloading of Wireless Sensor Network in Edge Computing Environment

学校读者我要写书评

暂无评论

Overview of Task Offloading of Wireless Sensor Network in Ed...

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： XiQiang Hou YiFan Hu Fuqiang Wang School of information and control engineering Qingdao University of Technology Qingdao China Shandong Computer Science Center and Shandong Provincial Key Laboratory of Computer Networks Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Computer Science Center and Shandong Provincial Key Laboratory of Computer Networks Qilu University of Technology (Shandong Academy of Sciences) China

This review article introduces the concepts, server architecture and application scenarios of Mobile Edge Computing (MEC) and Wireless Sensor Network (WSN). By differentiating between rechargeable and non-rechargeable systems, it presents the research status of task offloading in WSN in an edge computing environment. Various strategies are analyzed and compared in terms of their characteristics and application domains. The existing methods can reduce offloading latency and energy consumption, but still face some issues. Based on this, the research hotspots of edge computing task offloading for WSN are summarized, and its research and development trends are pointed out.

关键词：

Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis

学校读者我要写书评

暂无评论

Memory-Friendly Scalable Super-Resolution via Rewinding Lott...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jin Lin Xiaotong Luo Ming Hong Yanyun Qu Yuan Xie Zongze Wu School of Informatics Xiamen University Fujian China School of Computer Science and Technology East China Normal University Shanghai China School of Mechatronics and Control Engineering Shenzhen University Shenzhen China

Scalable deep Super-Resolution (SR) models are increasingly in demand, whose memory can be customized and tuned to the computational recourse of the platform. The existing dynamic scalable SR methods are not memory-friendly enough because multi-scale models have to be saved with a fixed size for each model. Inspired by the success of Lottery Tickets Hypothesis (LTH) on image classification, we explore the existence of unstructured scalable SR deep models, that is, we find gradual shrinkage subnetworks of extreme sparsity named winning tickets. In this paper, we propose a Memory-friendly Scalable SR framework (MSSR). The advantage is that only a single scalable model covers multiple SR models with different sizes, instead of reloading SR models of different sizes. Concretely, MSSR consists of the forward and backward stages, the former for model compression and the latter for model expansion. In the forward stage, we take advantage of LTH with rewinding weights to progressively shrink the SR model and the pruning-out masks that form nested sets. Moreover, stochastic self-distillation (SSD) is conducted to boost the performance of sub-networks. By stochastically selecting multiple depths, the current model inputs the selected features into the corresponding parts in the larger model and improves the performance of the current model based on the feedback results of the larger model. In the backward stage, the smaller SR model could be expanded by recovering and fine-tuning the pruned parameters according to the pruning-out masks obtained in the forward. Extensive experiments show the effectiveness of MMSR. The smallest-scale sub-network could achieve the sparsity of 94% and outperforms the compared lightweight SR methods.

关键词：

Distributed switched model-based predictive control for distributed large-scale systems with switched topology

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ahandani, Morteza Alinia Kharrati, Hamed Hashemzadeh, Farzad Baradarannia, Mahdi Department of Control Engineering Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran

Distributed switched large-scale systems are composed by dynamically coupled subsystems, in which interactions among subsystems vary over time according to an exogenous input signal named switching signal. In this paper, we present a distributed robust switched model-based predictive control (DSwMPC) to control such systems that are subject to local state/input constraints. The proposed method guarantees stabilizing the origin of the whole closed-loop system and ensures the constraints satisfaction in the presence of an unknown switching signal. In the distributed model-based predictive control (DMPC) used in this work, by considering the interactions among subsystems as an additive disturbance, the effect of the switch is reflected on the dynamic equation, local, and consistency constraint sets of the nominal subsystems. In the DSwMPC, to compensate the effect of switching signal which creates a time-varying network topology, a robust tube-based switched model-based predictive control (RSwMPC) with switch–robust control invariant (switch-RCI) set as the target set robust to unknown mode switching is used as local controller. The scheme performance is assessed using three typical examples. In the first example, the switching times are unknown in prior, but the next neighborhood sets are assumed to be known in prior. In the second and third cases, both of them are supposed to be unknown in prior. The simulation results show that the input and state constraints are satisfied by the proposed DSwMPC at all times. They also validate that the closed-loop system converges to the origin. Also, to demonstrate the performance of the proposed DSwMPC more clearly, a comparison of the DSwMPC with a centralized SwMPC (CSwMPC) and a decentralized SwMPC (DeSwMPC) shows that the DSwMPC outperforms the DecSwMPC and also the shapes of response curves under the CSwMPC are very similar to those obtained by the DSwMPC. © 2021, CC BY.

关键词： Large scale systems

Algorithmically Fair Maximization of Multiple Submodular Objective Functions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Amanatidis, Georgios Birmpas, Georgios Lazos, Philip Leonardi, Stefano Reiffenhäuser, Rebecca School of Mathematics Statistics and Actuarial Science University of Essex United Kingdom Archimedes / Athena RC Greece Department of Computer Science University of Liverpool United Kingdom London United Kingdom Department of Computer Control and Management Engineering Sapienza University of Rome Italy Institute for Logic Language and Computation University of Amsterdam Netherlands

Constrained maximization of submodular functions poses a central problem in combinatorial optimization. In many realistic scenarios, a number of agents need to maximize multiple submodular objectives over the same ground set. We study such a setting, where the different solutions must be disjoint, and thus, questions of algorithmic fairness arise. Inspired from the fair division literature, we suggest a simple round-robin protocol, where agents are allowed to build their solutions one item at a time by taking turns. Unlike what is typical in fair division, however, the prime goal here is to provide a fair algorithmic environment;each agent is allowed to use any algorithm for constructing their respective solutions. We show that just by following simple greedy policies, agents have solid guarantees for both monotone and non-monotone objectives, and for combinatorial constraints as general as p-systems (which capture cardinality and matroid intersection constraints). In the monotone case, our results include approximate EF1-type guarantees and their implications in fair division may be of independent interest. Further, although following a greedy policy may not be optimal in general, we show that consistently performing better than that is computationally hard. Copyright © 2024, The Authors. All rights reserved.

关键词： Combinatorial optimization

Risk-Sensitive Reinforcement Learning with Exponential Criteria

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Noorani, Erfaun Mavridis, Christos N. Baras, John S. Department of Electrical and Computer Engineering the Institute for Systems Research University of Maryland College Park United States Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

While reinforcement learning has shown experimental success in a number of applications, it is known to be sensitive to noise and perturbations in the parameters of the system, leading to high variability in the total reward amongst different episodes on slightly different environments. To introduce robustness, as well as sample efficiency, risk-sensitive reinforcement learning methods are being thoroughly studied. In this work, we provide a definition of robust reinforcement learning policies and formulate a risk-sensitive reinforcement learning problem to approximate them, by solving an optimization problem with respect to a modified objective based on exponential criteria. In particular, we study a model-free risk-sensitive variation of the widely-used Monte Carlo Policy Gradient algorithm, and introduce a novel risk-sensitive online Actor-Critic algorithm based on solving a multiplicative Bellman equation using stochastic approximation updates. Analytical results suggest that the use of exponential criteria generalizes commonly used ad-hoc regularization approaches, improves sample efficiency, and introduces robustness with respect to perturbations in the model parameters and the environment. The implementation, performance, and robustness properties of the proposed methods are evaluated in simulated experiments. © 2022, CC BY.

关键词： Contrastive Learning

MD-SLAM: Multi-cue Direct SLAM

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Di Giammarino, Luca Brizi, Leonardo Guadagnino, Tiziano Stachniss, Cyrill Grisetti, Giorgio The Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Italy The University of Bonn Germany The Department of Engineering Science The University of Oxford United Kingdom

Simultaneous Localization and Mapping (SLAM) systems are fundamental building blocks for any autonomous robot navigating in unknown environments. The SLAM implementation heavily depends on the sensor modality employed on the mobile platform. For this reason, assumptions on the scene’s structure are often made to maximize estimation accuracy. This paper presents a novel direct 3D SLAM pipeline that works independently for RGB-D and LiDAR sensors. Building upon prior work on multi-cue photometric frame-to-frame alignment [4], our proposed approach provides an easy-to-extend and generic SLAM system. Our pipeline requires only minor adaptations within the projection model to handle different sensor modalities. We couple a position tracking system with an appearance-based relocalization mechanism that handles large loop closures. Loop closures are validated by the same direct registration algorithm used for odometry estimation. We present comparative experiments with state-of-the-art approaches on publicly available benchmarks using RGB-D cameras and 3D LiDARs. Our system performs well in heterogeneous datasets compared to other sensor-specific methods while making no assumptions about the environment. Finally, we release an open-source C++ implementation of our system. Copyright © 2022, The Authors. All rights reserved.

关键词： Pipelines

Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Daghero, Francesco Xie, Chen Pagliari, Daniele Jahier Burrello, Alessio Castellano, Marco Gandolfi, Luca Calimera, Andrea Macii, Enrico Poncino, Massimo Department of Control and Computer Engineering Politecnico di Torino Turin Italy Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy STMicroelectronics Cornaredo Italy

Human Activity Recognition (HAR) is a relevant inference task in many mobile applications. State-of-the-art HAR at the edge is typically achieved with lightweight machine learning models such as decision trees and Random Forests (RFs), whereas deep learning is less common due to its high computational complexity. In this work, we propose a novel implementation of HAR based on deep neural networks, and precisely on Binary Neural Networks (BNNs), targeting low-power general purpose processors with a RISC-V instruction set. BNNs yield very small memory footprints and low inference complexity, thanks to the replacement of arithmetic operations with bit-wise ones. However, existing BNN implementations on general purpose processors impose constraints tailored to complex computer vision tasks, which result in over-parametrized models for simpler problems like HAR. Therefore, we also introduce a new BNN inference library, which targets ultra-compact models explicitly. With experiments on a single-core RISC-V processor, we show that BNNs trained on two HAR datasets obtain higher classification accuracy compared to a state-of-the-art baseline based on RFs. Furthermore, our BNN reaches the same accuracy of a RF with either less memory (up to 91%) or more energy-efficiency (up to 70%), depending on the complexity of the features extracted by the RF. © 2022, CC BY.

关键词： Energy efficiency

Analysis and Design of a New Type of Polymer-Magnet Permanent Magnet Fault-Tolerant Vernier Motor

学校读者我要写书评

暂无评论

Analysis and Design of a New Type of Polymer-Magnet Permanen...

China International Electrical and Energy Conference (CIEEC)

作者： Dan Li Yuhao Cao Bo Wang College of Computer and Control Engineering Northeast Forestry University Harbin China General Manager of Digital People's Livelihood Department Heilongjiang Branch China Telecom Digital Intelligence Technology Co. Ltd. Harbin China

ISBN: (数字)9798350359558

ISBN: (纸本)9798350359565

This study focuses on the Spoke Array Fault-Tolerant Permanent Magnet Vernier Machine (SAFTPMVM) which, due to its magnetic concentration effect, has a high torque density. However, an increase in air gap length significantly affects this magnetic concentration, thereby drastically reducing the motor's torque density. To address this issue, a new structure called the Fault-Tolerant Concentrated Flux Permanent Magnet Vernier Machine (FCFTPMVM) is proposed. This structure enhances the fundamental and low-order harmonic of the air gap magnetic density, thus increasing torque density without additional permanent magnet material. The principle of torque enhancement was analyzed using the equivalent magnetic circuit method, and the impact of structural parameters on torque performance was studied using finite element methods. This led to the design of optimal motor structural parameters. A comparative analysis of the electromagnetic performance of surface-mounted, spoke array, and the new concentrated flux structure motors was conducted using finite element analysis. The results demonstrate that the proposed FCFTPMVM motor exhibits high output torque, low torque ripple, high efficiency, and strong fault tolerance capabilities.

关键词： Fault tolerance Magnetic flux Torque Fault tolerant systems Air gaps Motors Permanent magnets

Incorporating Extended Reality Technology for Delivering computer Aided Design and Visualisation Modules

学校读者我要写书评

暂无评论

Incorporating Extended Reality Technology for Delivering Com...

International Conference on Software, Knowledge Information, Industrial Management and Applications (SKIMA)

作者： Parag Vichare Michele Cano Keshav Dahal Tomasz Siewierski Marco Gilardi School of Computing Engineering and Physical Sciences (CEPS) University of the West of Scotland Paisley Faculty of Electrical Electronic Computer and Control Engineering Lodz University of Technology Lodz Poland

ISBN: (纸本)9781665493352

The basic requirement in curriculum design is to review and constructively align programme modules with state-of-the art and trends in the subject area. Extended reality (XR), an umbrella term for emerging technologies such as augmented reality (AR), mixed reality (MR) and virtual reality (VR), is becoming a prominent aspect of design and visualization for architecture, engineering, and construction (AEC) industry. engineering programmes are primary feeders for the AEC industry, delivery of CAD and visualisation modules provide wider opportunities for adapting such emerging technologies in the subject area, as well as use of these technologies for developing novel pedagogical practices. This paper provides a rational behind revising traditional CAD and visualisation modules designed for engineering undergraduate programmes, and constructively incorporate XR within programme modules. A critical literature review is provided on XR subject area as well as XR based pedagogical practices. This review identifies elements of XR as a subject area that can be incorporated in AEC programmes. It also highlights academic and operational considerations in adapting XR technology for delivering CAD and visualisation modules. Similar approach is extended to evaluate integration of XR technologies for Electrical and Power engineering Programmes.

关键词： Industries Visualization Power engineering Three-dimensional displays Extended reality Education Mixed reality