检索结果-内蒙古大学图书馆

Integration of Mixture of Experts and Multimodal Generative AI in Internet of Vehicles: A Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Minrui Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Fang, Yuguang Kim, Dong In Shen, Xuemin The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The School of Electrical and Information Engineering University of Sydney SydneyNSW2006 Australia Department of Computer Science City University of Hong Kong Kowloon Hong Kong The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

Generative AI (GAI) can enhance the cognitive, reasoning, and planning capabilities of intelligent modules in the Internet of Vehicles (IoV) by synthesizing augmented datasets, completing sensor data, and making sequential decisions. In addition, the mixture of experts (MoE) can enable the distributed and collaborative execution of AI models without performance degradation between connected vehicles. In this survey, we explore the integration of MoE and GAI to enable Artificial General Intelligence in IoV, which can enable the realization of full autonomy for IoV with minimal human supervision and applicability in a wide range of mobility scenarios, including environment monitoring, traffic management, and autonomous driving. In particular, we present the fundamentals of GAI, MoE, and their interplay applications in IoV. Furthermore, we discuss the potential integration of MoE and GAI in IoV, including distributed perception and monitoring, collaborative decision-making and planning, and generative modeling and simulation. Finally, we present several potential research directions for facilitating the integration. © 2024, CC BY.

关键词： Integration

No One Left Behind: Real-World Federated Class-Incremental Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dong, Jiahua Li, Hongliu Cong, Yang Sun, Gan Zhang, Yulun Van Gool, Luc The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China The University of Chinese Academy of Sciences Beijing100049 China The Department of Civil and Environmental Engineering Hong Kong Polytechnic University Hong Kong The College of Automation Science and Engineering South China University of Technology Guangzhou510640 China The Computer Vision Lab ETH Zürich Zürich8092 Switzerland

Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available at https://***/JiahuaDong/LGA. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

Jet mixing enhancement with Bayesian optimization, deep learning, and persistent data topology

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Yiqing Noack, Bernd R. Wang, Tianyu Cornejo Maceda, Guy Y. Pickering, Ethan Shaqarin, Tamir Tyliszczak, Artur School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Harbin Institute of Technology Shenzhen518055 China Department of Mechanical Engineering Tafila Technical University Tafila66110 Jordan Faculty of Mechanical Engineering and Computer Science Czestochowa University of Technology Czestochowa42-201 Poland

We optimize the jet mixing using large eddy simulations (LES) at a Reynolds number of 3000. Key methodological enablers consist of Bayesian optimization, a surrogate model enhanced by deep learning, and persistent data topology for physical interpretation. The mixing performance is characterized by an equivalent jet radius (Req) derived from the streamwise velocity in a plane located 8 diameters downstream. The optimization is performed in a 22-dimensional actuation space that comprises most known excitations. The plant benefits from a 22-dimensional actuation space that comprises most known excitations. This search space parameterizes distributed actuation imposed on the bulk flow and at the periphery of the nozzle in the streamwise and radial directions. The momentum flux measures the energy input of the actuation. The optimization quadruples the jet radius Req with a 7-armed blooming jet after around 570 evaluations. The control input requires 2% momentum flux of the main flow, which is one order of magnitude lower than an ad hoc dual-mode excitation. Intriguingly, a pronounced suboptimum in the search space is associated with a double-helix jet, a new flow pattern. This jet pattern results in a mixing improvement comparable to the blooming jet. A state-of-the-art Bayesian optimization converges towards this double helix solution. The learning is accelerated and converges to another better optimum by including surrogate model trained along the optimization. Persistent data topology extracts the global and many local minima in the actuation space. These minima can be identified with flow patterns beneficial to the mixing. © 2023, CC BY-NC-ND.

关键词： Flow patterns

On Enlarging the Domain of Attraction for Linear Systems Subject to Asymmetric Actuator Saturation

学校读者我要写书评

暂无评论

On Enlarging the Domain of Attraction for Linear Systems Sub...

IEEE Conference on Decision and Control

作者： Wenxin Lai Yuanlong Li Zongli Lin Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Charlottesville VA U.S.A.

In this paper, we revisit the problem of enlarging the domain of attraction for linear systems with asymmetric actuator saturation. We partition the state space into several regions according to the sign of each input and rewrite the linear system subject to asymmetric actuator saturation as an equivalent switched system, each subsystem of which is associated with one partition of the state space and is a linear system subject to symmetric actuator saturation. Based on this equivalent representation of the system, we present a Lyapunov function, which is composed of a set of quadratic functions associated with matrices that are not required to be positive definite. We establish sufficient conditions for regional stability and, based on them, formulate optimization problems to enlarge the estimate of the domain of attraction. Simulation results illustrate the effectiveness of the proposed approach.

关键词：

An Improved Method for Approximating the Infinite-horizon Value Function of the Discrete-time Switched LQR Problem

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2023年第2期56卷 4138-4143页

作者： Tan Hou Yuanlong Li Zongli Lin Department of Automation Shanghai Jiao Tong University Shanghai 200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240 China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia P.O. Box 400743 Charlottesville VA 22904-4743 U.S.A.

This paper considers the problem of approximating the infinite-horizon value function of the discrete-time switched LQR problem. In particular, we propose a new value iteration method to generate a sequence of monotonically decreasing functions that converges exponentially to the value function. This method facilitates us to use coarse approximations resulting from faster but less accurate algorithms for further value iteration, and thus, our method is capable of achieving a better approximation for a given computation time compared with the existing methods. Two numerical examples are presented in this paper to illustrate the effectiveness of our method.

关键词： Switched linear systems optimal control switched LQR problem

Neural Augmentation Based Panoramic High Dynamic Range Stitching

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Chaobing Xu, Yilun Chen, Weihai Wu, Shiqian Zhang, Sen Li, Zhengguo Institute of Robotics and Intelligent Systems School of Electronic Information Wuhan University of Science and Technology 947 Heping Avenue Wuhan430081 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China School of Automation and Electrical Engineering University of Science and Technology Beiing Beijing100083 China Key Laboratory of Knowledge Auomalion for indusrial Proceses of Mimistry ofEducation University of Science and Techmology Beijing Beijing1083 China Shunde lnnovation School University of Science and Technology Beijing Foshan 528300 China VI Department Institute for Infocomm Research A*STAR 138632 Singapore

Due to saturated regions of inputting low dynamic range (LDR) images and large intensity changes among the LDR images caused by different exposures, it is challenging to produce an information enriched panoramic LDR image without visual artifacts for a high dynamic range (HDR) scene through stitching multiple geometrically synchronized LDR images with different exposures and pairwise overlapping fields of views (OFOVs). Fortunately, the stitching of such images is innately a perfect scenario for the fusion of a physics-driven approach and a data-driven approach due to their OFOVs. Based on this new insight, a novel neural augmentation based panoramic HDR stitching algorithm is proposed in this paper. The physics-driven approach is built up using the OFOVs. Different exposed images of each view are initially generated by using the physics-driven approach, are then refined by a data-driven approach, and are finally used to produce panoramic LDR images with different exposures. All the panoramic LDR images with different exposures are combined together via a multi-scale exposure fusion algorithm to produce the final panoramic LDR image. Experimental results demonstrate the proposed algorithm outperforms existing panoramic stitching algorithms. © 2024, CC0.

关键词： Image fusion

Automated Leukemia Screening and Sub-types Classification Using Deep Learning

学校读者我要写书评

暂无评论

computer Systems Science & engineering 2023年第9期46卷 3541-3558页

作者： Chaudhary Hassan Abbas Gondal Muhammad Irfan Sarmad Shafique Muhammad Salman Bashir Mansoor Ahmed Osama M.Alshehri Hassan H.Almasoudi Samar M.Alqhtani Mohammed M.Jalal Malik A.Altayar Khalaf F.Alsharif Department of Computer Science COMSATS University Islamabad44000Pakistan Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia Control Automotive and Robotics LabNational Center of Robotics and Automation(NCRA HEC)MirpurPakistan Mirpur University of Science and Technology(MUST)MirpurPakistan Department of Computer Science Virtual University of PakistanLahore54000Pakistan Department of Clinical Laboratory Sciences College of Applied Medical SciencesNajran UniversityNajran61441Saudi Arabia Department of Information Systems College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Department of Medical Laboratory Technology Faculty of Applied Medical SciencesUniversity of TabukTabukSaudi Arabia Department of Clinical Laboratory Sciences College of Applied Medical SciencesTaif UniversityP.O.Box 11099Taif21944Saudi Arabia

Leukemia is a kind of blood cancer that damages the cells in the blood and bone marrow of the human *** produces cancerous blood cells that disturb the human’s immune system and significantly affect bone marrow’s production ability to effectively create different types of blood cells like red blood cells(RBCs)and white blood cells(WBC),and *** can be diagnosed manually by taking a complete blood count test of the patient’s blood,from which medical professionals can investigate the signs of leukemia ***,two other methods,microscopic inspection of blood smears and bone marrow aspiration,are also utilized while examining the patient for ***,all these methods are labor-intensive,slow,inaccurate,and require a lot of human experience and *** authors have proposed automated detection systems for leukemia diagnosis to overcome these *** have deployed digital image processing and machine learning algorithms to classify the cells into normal and blast ***,these systems are more efficient,reliable,and fast than previous manual diagnosing ***,more work is required to classify leukemia-affected cells due to the complex characteristics of blood images and leukemia cells having much intra-class variability and inter-class *** this paper,we have proposed a robust automated system to diagnose leukemia and its *** have classified ALL into its sub-types based on FAB classification,i.e.,L1,L2,and L3 types with better *** have achieved 96.06%accuracy for subtypes classification,which is better when compared with the state-of-the-art methodologies.

关键词： Healthcare cancer detection deep learning convolutional neural network

Distributed Constrained Online Nonconvex Optimization with Compressed Communication

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Kunpeng Xu, Lei Yi, Xinlei Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Mechanical Engineering University of Victoria VictoriaBCV8W 2Y2 Canada Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai201210 China Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper considers distributed online nonconvex optimization with time-varying inequality constraints over a network of agents. For a time-varying graph, we propose a distributed online primal–dual algorithm with compressed communication to efficiently utilize communication resources. We show that the proposed algorithm establishes an O(T max{1−θ1,θ1}) network regret bound and an O(T 1−θ1/2) network cumulative constraint violation bound, where T is the number of iterations and θ1 ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds (i.e, there is a point that strictly satisfies the inequality constraints at all iterations), the network cumulative constraint violation bound is reduced to O(T 1−θ1). These bounds are comparable to the state-of-the-art results established by existing distributed online algorithms with perfect communication for distributed online convex optimization with (time-varying) inequality constraints. Finally, a simulation example is presented to validate the theoretical results. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

Cognitive Disentanglement for Referring Multi-Object Tracking

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liang, Shaofeng Guan, Runwei Lian, Wangwang Liu, Daizong Sun, Xiaolou Wu, Dongming Yue, Yutao Ding, Weiping Xiong, Hui Qingdao China Guangzhou China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao China Wangxuan Institute of Computer Technology Peking University Beijing China School of Automation Southeast University Nanjing China School of Computer Science Beijing Institute of Technology Beijing China School of Artificial Intelligence and Computer Science Nantong University Nantong China Guangzhou China Department of Electrical Engineering and Electronics University of Liverpool Liverpool United Kingdom

As a significant application of multi-source information fusion in intelligent transportation perception systems, Referring Multi-Object Tracking (RMOT) involves localizing and tracking specific objects in video sequences based on language references. However, existing RMOT approaches often treat language descriptions as holistic embeddings and struggle to effectively integrate the rich semantic information contained in language expressions with visual features. This limitation is especially apparent in complex scenes requiring comprehensive understanding of both static object attributes and spatial motion information. In this paper, we propose a Cognitive Disentanglement for Referring Multi-Object Tracking (CDRMT) framework that addresses these challenges. It adapts the "what" and "where" pathways from the human visual processing system to RMOT tasks. Specifically, our framework first establishes cross-modal connections while preserving modality-specific characteristics. It then disentangles language descriptions and hierarchically injects them into object queries, refining object understanding from coarse to fine-grained semantic levels. Finally, we reconstruct language representations based on visual features, ensuring that tracked objects faithfully reflect the referring expression. Extensive experiments on different benchmark datasets demonstrate that CDRMT achieves substantial improvements over state-of-the-art methods, with average gains of 6.0% in HOTA score on Refer-KITTI and 3.2% on Refer-KITTI-V2. Our approach advances the state-of-the-art in RMOT while simultaneously providing new insights into multi-source information fusion. Copyright © 2025, The Authors. All rights reserved.

关键词： Object detection