检索结果-内蒙古大学图书馆

GLCONet: Learning Multi-source Perception Representation for Camouflaged Object Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Yanguang Xuan, Hanyu Yang, Jian Luo, Lei The PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China The School of Big Data and Statistics Anhui University Hefei230601 China

Recently, biological perception has been a powerful tool for handling the camouflaged object detection (COD) task. However, most existing methods are heavily dependent on the local spatial information of diverse scales from convolutional operations to optimize initial features. A commonly neglected point in these methods is the long-range dependencies between feature pixels from different scale spaces that can help the model build a global structure of the object, inducing a more precise image representation. In this paper, we propose a novel Global-Local Collaborative Optimization Network, called GLCONet. Technically, we first design a collaborative optimization strategy from the perspective of multi-source perception to simultaneously model the local details and global long-range relationships, which can provide features with abundant discriminative information to boost the accuracy in detecting camouflaged objects. Furthermore, we introduce an adjacent reverse decoder that contains cross-layer aggregation and reverse optimization to integrate complementary information from different levels for generating high-quality representations. Extensive experiments demonstrate that the proposed GLCONet method with different backbones can effectively activate potentially significant pixels in an image, outperforming twenty state-of-the-art methods on three public COD datasets. The source code is available at: https://***/CSYSI/GLCONet. © 2024, CC BY.

关键词： Object detection

Open-World Semi-Supervised Learning for Node Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yanling Zhang, Jing Zhang, Lingxi Liu, Lixin Dong, Yuxiao Li, Cuiping Chen, Hong Yin, Hongzhi School of Information Renmin University of China China Zhongguancun Laboratory China Alibaba Group China Department of Computer Science and Technology Tsinghua University China School of Information Technology and Electrical Engineering The University of Queensland Australia

Open-world semi-supervised learning (Open-world SSL) for node classification, that classifies unlabeled nodes into seen classes or multiple novel classes, is a practical but under-explored problem in the graph community. As only seen classes have human labels, they are usually better learned than novel classes, and thus exhibit smaller intra-class variances within the embedding space (named as imbalance of intra-class variances between seen and novel classes). Based on empirical and theoretical analysis, we find the variance imbalance can negatively impact the model performance. Pre-trained feature encoders can alleviate this issue via producing compact representations for novel classes. However, creating general pre-trained encoders for various types of graph data has been proven to be challenging. As such, there is a demand for an effective method that does not rely on pre-trained graph encoders. In this paper, we propose an IMbalance-Aware method named OpenIMA for Open-world semi-supervised node classification, which trains the node classification model from scratch via contrastive learning with bias-reduced pseudo labels. Extensive experiments on seven popular graph benchmarks demonstrate the effectiveness of OpenIMA, and the source code has been available on GitHub1 © 2024, CC BY.

关键词： Signal encoding

Optimizing Bidding Curves for Renewable Energy in Two-Settlement Electricity Markets

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Dongwei Delikaraoglou, Stefanos Dvorkin, Vladimir Lamadrid, Alberto J.L. Botterud, Audun Argonne National Laboratory LemontIL United States Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA United States Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States Department of Economics Department of Industrial and Systems Engineering Lehigh University BethlehemPA United States

Coordination of day-ahead and real-time electricity markets is imperative for cost-effective electricity supply and also to provide efficient incentives for the energy transition. Although stochastic market designs feature the least-cost coordination, they are incompatible with current deterministic markets. This paper proposes a new approach for compatible coordination in two-settlement markets based on benchmark bidding curves for variable renewable energy. These curves are optimized based on a bilevel optimization problem, anticipating per-scenario responses of deterministic market-clearing problems and ultimately minimizing the expected cost across day-ahead and real-time markets. Although the general bilevel model is challenging to solve, we theoretically prove that a single-segment bidding curve with a zero bidding price is sufficient to achieve system optimality if the marginal cost of variable renewable energy is zero, thus addressing the computational challenge. In practice, variable renewable energy producers can be allowed to bid multi-segment curves with non-zero prices. We test the bilevel framework for both single- and multiple-segment bidding curves under the assumption of fixed bidding prices. We leverage duality theory and McCormick envelopes to derive the linear programming approximation of the bilevel problem, which scales to practical systems such as a 1576-bus NYISO system. We benchmark the proposed coordination and find absolute dominance over the baseline solution, which assumes that renewables agnostically bid their expected forecasts. We also demonstrate that our proposed scheme provides a good approximation of the least-cost, yet unattainable in practice, stochastic market outcome. © 2025, CC BY.

关键词：

Dual-domain Defenses for Byzantine-resilient Decentralized Resource Allocation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Runhua Ling, Qing Tian, Zhi The School of Computer Science and Engineering The Guangdong Provincial Key Laboratory of Computational Science Sun Yat-Sen University Guangdong Guangzhou510006 China The Department of Electrical and Computer Engineering George Mason University FairfaxVA22030 United States

This paper investigates the problem of decentralized resource allocation in the presence of Byzantine attacks. Such attacks occur when an unknown number of malicious agents send random or carefully crafted messages to their neighbors, aiming to prevent the honest agents from reaching the optimal resource allocation strategy. We characterize these malicious behaviors with the classical Byzantine attacks model, and propose a class of Byzantine-resilient decentralized resource allocation algorithms augmented with dual-domain defenses. The honest agents receive messages containing the (possibly malicious) dual variables from their neighbors at each iteration, and filter these messages with robust aggregation rules. Theoretically, we prove that the proposed algorithms can converge to neighborhoods of the optimal resource allocation strategy, given that the robust aggregation rules are properly designed. Numerical experiments are conducted to corroborate the theoretical results. Copyright © 2023, The Authors. All rights reserved.

关键词： Decentralized control

Free-space beam shaping and steering based on a silicon optical phased array

学校读者我要写书评

暂无评论

Photonics Research 2023年第12期11卷 2093-2099页

作者： WENBO REN QINGQING LIANG JIJUN FENG HAIPENG LIU JIANHUA HU SHUO YUAN XINCHENG XIA WEI JIANG QIWEN ZHAN HEPING ZENG Shanghai Key Laboratory of Modern Optical System Engineering Research Center of Optical Instrument and System(Ministry of Education)School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Chongqing Key Laboratory of Precision Optics Chongqing Institute of East China Normal UniversityChongqing 401120China State Key Laboratory of Precision Spectroscopy East China Normal UniversityShanghai 200241China

In this study,we present a method for free-space beam shaping and steering based on a silicon optical phased array,which addresses the theoretical limitation of traditional bulk *** theoretically analyze the beam propagation properties with changes in the applied *** beam profiles can be shaped by varying the phase combination,while a high-order quasi-Bessel beam can be generated with a cubic change to the phase *** simulated results are validated further experimentally,and they match one another *** steering can be achieved with a field of view as large as 140°,which has potential benefits for practical *** presented method is expected to have broad application prospects for optical communications,free-space optical interconnects,and light detection and ranging.

关键词： optical beam optics

Distributed Computation Offloading Based on Deep Reinforcement Learning and Blockchain in Internet of Vehicles

学校读者我要写书评

暂无评论

Distributed Computation Offloading Based on Deep Reinforceme...

IEEE International Conference on Communications in China (ICCC)

作者： Guobin Zhang Zehao Luo Tingting Yang School of Electrical Engineering and Intelligentization Dongguan University of Technology Dongguan China School of Computer Science and Technology Dongguan University of Technology Dongguan China Pengcheng Laboratory Shenzhen China

With the rapid development of Internet of Vehicles (IoV), the traditional centralized cloud computing cannot efficiently satisfy the computation requirements of vehicles. The deployment of mobile edge server (MEC) on road side unit (RSU) can shorten the distance between vehicles and computing servers so as to reduce the service delay. In order to provide wide coverage and more computation resources, we introduce high altitude platform system (HAPS) as a central node for computation controlling in the IoV system. To improve data security and user privacy, blockchain technology is applied to verify and determine the offloading strategy between RSUs. Aiming at minimizing the sum of the transmission and computation time, an optimization problem is formulated under the power and offloading constraints. The deep reinforcement learning (DRL) with the soft actor-critic (SAC) algorithm is utilized to solve the problem. Simulation results demonstrate the time reduction by the application of HAPS and significant superiority of the proposed scheme compared to the existing approaches.

关键词：

Differentially Private Reward Functions for Markov Decision Processes

学校读者我要写书评

暂无评论

Differentially Private Reward Functions for Markov Decision ...

Control Technology and Applications (CCTA),

作者： Alexander Benvenuti Calvin Hawkins Brandon Fallin Bo Chen Brendan Bialy Miriam Dennis Matthew Hale School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA Department of Mechanical and Aerospace Engineering University of Florida Gainesville FL USA Munitions Directorate Air Force Research Laboratory FL USA

ISBN: (数字)9798350370942

ISBN: (纸本)9798350370959

Markov decision processes often seek to maximize a reward function, but onlookers may infer reward functions by observing agents, which can reveal sensitive information. Therefore, in this paper we introduce and compare two methods for privatizing reward functions in policy synthesis for multi-agent Markov decision processes, which generalize Markov decision processes. Reward functions are privatized using differential privacy, a statistical framework for protecting sensitive data. The methods we develop perturb (i) each agent’s individual reward function or (ii) the joint reward function shared by all agents. We prove that both of these methods are differentially private and show approach (i) provides better performance. We then develop an algorithm for the numerical computation of the performance loss due to privacy on a case-by-case basis. We also exactly compute the computational complexity of this algorithm in terms of system parameters and show that it is inherently tractable. Numerical simulations are performed on waypoint guidance of an autonomous vehicle which shows that privacy induces only negligible performance losses in practice.

关键词： Privacy Differential privacy Accuracy Markov decision processes Perturbation methods Observers Numerical simulation

Advances of wearable silicone rubber-based triboelectric nanogenerators:from manufacturing to application

学校读者我要写书评

暂无评论

International Journal of Extreme Manufacturing 2025年第3期7卷 126-158页

作者： Dianlong Shen Taili Du Fangyang Dong Hu Cai Aziz Noor Xiannan Du Yongjiu Zou Chengkuo Lee Minyi Xu Dalian Key Laboratory of Marine Micro/Nano Energy and Self-Powered Systems Marine Engineering CollegeDalian Maritime UniversityDalian 116026People’s Republic of China State Key Laboratory of Maritime Technology and Safety Dalian 116026People’s Republic of China Collaborative Innovation Research Institute of Autonomous Ship Dalian Maritime UniversityDalian 116026People’s Republic of China Department of Electrical and Computer Engineering National University of Singapore4 Engineering Drive 3Singapore 117576Singapore

Wearable bioelectronic devices are rapidly evolving towards miniaturization and multifunctionality,with remarkable features such as flexibility and ***,achieving a sustainable power supply for wearable bioelectronic devices is still a great *** nanogenerators(TENGs)provide an efficient solution by converting irregular,low-frequency bioenergy from the human body into electrical *** sustainably powering wearable bioelectronics,the harvested electrical energy also carries rich information for human body *** this conversion process,the choice of material plays a crucial role in affecting the output performance of the *** various materials,silicone rubber(SR)stands out due to its exceptional plasticity,flexibility,comfortability and other favorable ***,with appropriate treatment,SR can achieve extreme functionalities such as high robustness,good stability,self-healing capabilities,rapid response,and *** this review,recent advances in wearable SR-based TENGs(SR-TENGs)are systematically reviewed with a focus on their application in different parts of the human *** that the manufacturing method of SR-TENGs largely determines its output performance and sensitivity,this paper introduces the design of SR-TENGs,including material selection,process modulation,and structure ***,this article discusses the current challenges in the SR-TENG fabrication technology and potential future directions,aiming to promote the effective development of SR-TENGs in biomechanical energy harvesting and self-powered sensing applications.

关键词： extreme function silicone rubber triboelectric nanogenerators wearable bioelectronics energy harvesting self-powered sensing fabrication methods

Gemini+: Enhancing Real-Time Video Analytics with Dual-Image FPGAs

学校读者我要写书评

暂无评论

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年

作者： Wu, Jingrou Hu, Chuang Zhang, Jin Wang, Dan Jiang, Jing University of Technology Sydney Australian Artificial Intelligence Institute SydneyNSW2007 Australia Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems The Department of Computer Science and Engineering Shenzhen518055 China Wuhan University School of Computer Science Wuhan430072 China Southern University of Science and Technology Department of Computer Science and Engineering The Research Institute of Trustworthy Autonomous Systems Shenzhen518055 China Peng Cheng Laboratory Shenzhen518055 China Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong

Real-time video analytics demand intensive computing resources, often exceeding device capabilities. Heterogeneous computing resources like CPU and GPU, usually work collaboratively to ensure real-time performance. GPU manage data-intensive computing, while CPU handle instruction-intensive tasks. However, analytics accuracy can degrade because of the imbalance between CPU-GPU workloads and resources, and static resources in most systems limit adaptability to dynamic workloads. In addition to CPU-GPU resource control, accuracy is highly dependent on video analytics configuration including resolution, frame rate, and model selection. In this paper, we propose Gemini+, a hardware-accelerated video analytics pipeline empowered by dual-image FPGAs. It enables flexible CPU-GPU resource adaptation by providing near-instantaneous switching between two pre-configured images. We investigate CPU-GPU resource control and video analytics configuration adaptation in a dual-image FPGA-based video analytics pipeline. We study and formulate two problems of practical importance, a single-camera and multi-camera dual computing resource control problem, i.e., SC-DCRC and MC-DCRC. We analyze the problem complexity and develop optimal and sub-optimal algorithms. We evaluate our algorithms through simulation and build a prototype for verification. The results show that Gemini+ can improve analytic accuracy by 25% compared to fixed CPU-GPU resource systems and 88% compared to GPU-dominant systems. © 2025 IEEE.

关键词： Graphics processing unit