检索结果-内蒙古大学图书馆

Resource Allocation for Reliable Transmission in IRS-Assisted Industrial Wireless Sensor Networks 18th

学校读者我要写书评

暂无评论

Resource Allocation for Reliable Transmission in IRS-Assis...

18th China Conference on Wireless Sensor Networks, CWSN 2024

作者： Wang, Chuqing Zheng, Meng Liang, Wei Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9789819621880

Intelligent Reflecting Surface (IRS) is one of the promising technologies for improving transmission reliability of Industrial Wireless Sensor Networks (IWSNs) by creating a virtual line-of-sight (LoS) link to bypass obstacles between transceivers. In this paper, we consider an IRS-assisted IWSN and propose a resource allocation method for reliable transmission in the IRS-assisted IWSN. First, a transmission reliability optimization problem in terms of the reflective beamforming at the IRS and the timeslot and power allocated to sensors is formulated. Second, the formulated optimization problem is transformed into an equivalent but simplified problem. In subsequent, a particle swarm optimization based method is utilized to obtain a near-optimal solution. Simulation results demonstrate that this work yields higher transmission reliabilities than existing benchmark schemes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Particle swarm optimization (PSO)

SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Hair

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Zidu Zhao, Jiankuo Xu, Miao Zhu, Xiangyu Lei, Zhen State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences China

3D Morphable Models (3DMMs) have played a pivotal role as a fundamental representation or initialization for 3D avatar animation and reconstruction. However, extending 3DMMs to hair remains challenging due to the difficulty of enforcing vertex-level consistent semantic meaning across hair shapes. This paper introduces a novel method, Semantic-consistent Ray Modeling of Hair (SRM-Hair), for making 3D hair morphable and controlled by coefficients. The key contribution lies in semantic-consistent ray modeling, which extracts ordered hair surface vertices and exhibits notable properties such as additivity for hairstyle fusion, adaptability, flipping, and thickness modification. We collect a dataset of over 250 high-fidelity real hair scans paired with 3D face data to serve as a prior for the 3D morphable hair. Based on this, SRM-Hair can reconstruct a hair mesh combined with a 3D head from a single image. Note that SRM-Hair produces an independent hair mesh, facilitating applications in virtual avatar creation, realistic animation, and high-fidelity hair rendering. Both quantitative and qualitative experiments demonstrate that SRM-Hair achieves state-of-the-art performance in 3D mesh reconstruction. Our project is available at https://***/wang-zidu/SRM-Hair. © 2025, CC BY-NC-ND.

关键词： Mesh generation

Dynamic Blockchain-Empowered Trustworthy End-Edge Collaborative Computing via Rotating Multi-Agent DRL

学校读者我要写书评

暂无评论

IEEE Transactions on Wireless Communications 2025年

作者： Xu, Chi Zhang, Peifeng Yu, Haibin Li, Yonghui Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang China University of Chinese Academy of Sciences Beijing China University of Sydney School of Electrical and Information Engineering Sydney Australia

Blockchain-empowered end-edge collaborative computing is a promising technology for enhancing the timeliness and trustworthiness of Industrial Internet of Things (IIoT). However, integrating task offloading with blockchain consensus inevitably escalates resource consumption across communication, computation, and energy domains. Thus, the joint optimization of task offloading, resource allocation and blockchain consensus is very important for IIoT. This paper studies a general end-edge collaborative computing scenario with multiple end devices and multiple edge servers. We first propose a novel dynamic blockchain (DBC) scheme by developing a dynamic leader election mechanism and designing a dynamic consensus waiting time window. Then, by fully considering the constraints of multi-task size and deadline, communication bandwidth, computing frequency, battery capacity, Byzantine fault tolerant and trustworthiness, we formulate the trustworthy processing efficiency (TPE) maximization problem with respect to end-edge task division, communication and computation resource allocation, leader election and consensus waiting window. To address this problem, we transform it into a Markov decision process and design a compound reward by fully considering the penalty for computing timeout and consensus failure. After that, we propose a rotating multi-agent deep reinforcement learning (R-MADRL) algorithm tailored to the proposed DBC scheme, where an entropy-based dual-critic DRL algorithm is proposed for rotating multi-agent training and decentralized execution. Extensive experiments validate the effectiveness and superiority of the proposed DBC with R-MADRL, where three benchmark DRL algorithms and three blockchain consensus schemes are compared. The results demonstrate that R-MADRL achieves stable convergence with more than 60.32% TPE reward than other algorithms while the task timeout ratio of DBC is reduced by more than 66.49% compared with other schemes. © 2025 institute of El

关键词： Markov processes

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery

学校读者我要写书评

暂无评论

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Ma, Shijie Zhu, Fei Zhang, Xu-Yao Liu, Cheng-Lin Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Hong Kong999077 Hong Kong

Generalized category discovery (GCD) is a pragmatic but underexplored problem, which requires models to automatically cluster and discover novel categories by leveraging the labeled samples from old classes. The challenge is that unlabeled data contain both old and new classes. Early works leveraging pseudo-labeling with parametric classifiers handle old and new classes separately, which brings about imbalanced accuracy between them. Recent methods employing contrastive learning neglect potential positives and are decoupled from the clustering objective, leading to biased representations and sub-optimal results. To address these issues, we introduce a unified and unbiased prototype learning framework, namely ProtoGCD, wherein old and new classes are modeled with joint prototypes and unified learning objectives, enabling unified modeling between old and new classes. Specifically, we propose a dual-level adaptive pseudo-labeling mechanism to mitigate confirmation bias, together with two regularization terms to collectively help learn more suitable representations for GCD. Moreover, for practical considerations, we devise a criterion to estimate the number of new classes. Furthermore, we extend ProtoGCD to detect unseen outliers, achieving task-level unification. Comprehensive experiments show that ProtoGCD achieves state-of-the-art performance on both generic and fine-grained datasets. ©1979-2012 IEEE.

关键词： Contrastive Learning

Towards Designing a Medication Assistive Intelligent System with Automated Insulin-dose Prediction for Elderlies

学校读者我要写书评

暂无评论

Towards Designing a Medication Assistive Intelligent System ...

International Conference on Electrical, Computer and Communication Engineering (ECCE)

作者： Abrar Ahmed Minhazul Islam Mahi M. Akhtaruzzaman Jamal Uddin Tanvin Fahim Shahryer Sachitra Halder Muhammad Towfiqur Rahman Md Shofiqul Islam Department of Computer Science and Engineering Military Institute of Science and Technology Dhaka Bangladesh Quantum Robotics and Automation Research Group (QRARG) Dhaka Bangladesh Department of Computer Science & Engineering University Asia Pacific (UAP) Dhaka Bangladesh Institute for Intelligent Systems Research and Innovation (IISRI) Deakin University Geelong Victoria

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Medication management poses significant challenges for many patients, particularly the elderlies, who often struggle with keeping track of their medication schedules and taking the correct dosages. To address this issue, this study aims to design an AI-integrated Medication Management and Assistive Unit (AMMAU) for elderlies with some important features like, schedule reminder, medicine recognition and count, early indication of shortage, sorted slots, and so on. Automated insulin-dose prediction and alert system makes the system unique and more demanding at these current scenarios. For this study, a suitable machine learning model is designed, analyzed, verified, and embedded in the proposed system so that the elderly diabetic patients can get alert, further compare with the current insulin-doses. Though, the proposed system is currently focusing on only the Basal insulin doses prediction, the system will definitely reduce the risks associated with wrong management of medication by degrading the chances of missed doses or taking wrong pills for elderlies at home.

关键词： Training Schedules Analytical models Prototypes Machine learning Predictive models Internet of Things Older adults Insulin Physical design

Stochastic Gradient Descent in Non-Convex Problems: Asymptotic Convergence with Relaxed Step-Size via Stopping Time Methods

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jin, Ruinan Cheng, Difei Qiao, Hong Shi, Xin Liu, Shaodong Zhang, Bo Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science Innovation Chinese Academy of Sciences New Territories Hong Kong Institute of Automation Chinese Academy of Sciences Beijing100190 China Shanghai Jiao Tong University Shanghai200240 China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

Stochastic Gradient Descent (SGD) is widely used in machine learning research. Previous convergence analyses of SGD under the vanishing step-size setting typically require Robbins–Monro conditions. However, in practice, a wider variety of step-size schemes are frequently employed, yet existing convergence results remain limited and often rely on strong assumptions. This paper bridges this gap by introducing a novel analytical framework based on a stopping-time method, enabling asymptotic convergence analysis of SGD under more relaxed step-size conditions and weaker assumptions. In the non-convex setting, we prove the almost sure convergence of SGD iterates for step-sizes (formula presented) and (formula presented) for some p > 2. Compared with previous studies, our analysis eliminates the global Lipschitz continuity assumption on the loss function and relaxes the boundedness requirements for higher-order moments of stochastic gradients. Building upon the almost sure convergence results, we further establish L2 convergence. These significantly relaxed assumptions make our theoretical results more general, thereby enhancing their applicability in practical *** Codes 40G15 Copyright © 2025, The Authors. All rights reserved.

关键词： Asymptotic analysis

Parameter Efficient Merging for Multimodal Large Language Models with Complementary Parameter Adaptation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zeng, Fanhu Guo, Haiyang Zhu, Fei Shen, Li Tang, Hao State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS Hong Kong School of Cyber Science and Technology Sun Yat-sen University China School of Computer Science Peking University China

Fine-tuning pre-trained models with custom data leads to numerous expert models on specific tasks. Merging models into one universal model to empower multi-task ability refraining from data leakage has gained popularity. With the expansion in data and model size, parameter efficient tuning becomes the common practice for obtaining task-specific models efficiently. However, we observe that existing methods designed for full fine-tuning merging fail under efficient tuning. To address the issues, we analyze from low-rank decomposition and reveal that maintaining direction and compensating for gap between singular values are crucial for efficient model merging. Consequently, we propose CoPA-Merging, a training-free parameter efficient merging method with complementary parameter adaptation. Specifically, we (1) prune parameters and construct scaling coefficients from inter-parameter relation to compensate for performance drop from task interference and (2) perform cross-task normalization to enhance unseen task generalization. We establish a benchmark consisting of diverse multimodal tasks, on which we conduct experiments to certificate the outstanding performance and generalizability of our method. Additional study and extensive analyses further showcase the effectiveness. Copyright © 2025, The Authors. All rights reserved.

关键词： Information leakage

Practical Continual Forgetting for Pre-trained Vision Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Hongbo Zhu, Fei Ni, Bolin Zhu, Feng Meng, Gaofeng Zhang, Zhaoxiang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100190 China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences 999077 Hong Kong SenseTime Research Beijing100084 China

For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests originate at any time from both users and model owners, and these requests usually form a sequence. Therefore, under such a setting, selective information is expected to be continuously removed from a pre-trained model while maintaining the rest. We define this problem as continual forgetting and identify three key challenges. (i) For unwanted knowledge, efficient and effective deleting is crucial. (ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal. (iii) In real-world scenarios, the training samples may be scarce or partially missing during the process of forgetting. To address them, we first propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we introduce LoRA modules to fine-tune the FFN layers in Transformer blocks for each forgetting task independently, and towards (ii), a simple group sparse regularization is adopted, enabling automatic selection of specific LoRA groups and zeroing out the others. To further extend GS-LoRA to more practical scenarios, we incorporate prototype information as additional supervision and introduce a more practical approach, GS-LoRA++. For each forgotten class, we move the logits away from its original prototype. For the remaining classes, we pull the logits closer to their respective prototypes. We conduct extensive experiments on face recognition, object detection and image classification and demonstrate that our method manages to forget specific classes with minimal impact on other classes. Codes have been released on https://***/bjzhb666/GS-LoRA. Copyright © 2025, The Authors. All rights reserved.

关键词： Face recognition

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ma, Shijie Zhu, Fei Zhang, Xu-Yao Liu, Cheng-Lin State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences 999077 Hong Kong

关键词： Semi-supervised learning