检索结果-内蒙古大学图书馆

Model Ownership Protection for Healthcare Consumer Electronics in Federated Edge Learning

IEEE Transactions on Consumer Electronics 2024年

作者： Wang, Rong Liang, Junchuan Feng, Chaosheng Chakraborty, Chinmay Alqahtani, Fayez Yu, Keping Sichuan Normal University College of Computer Science Chengdu610101 China Sichuan Normal University Visual Computing and Virtual Reality Key Laboratory of Sichuan Chengdu610068 China Birla Institute of Technology Mesra India King Saud University College of Computer and Information Sciences Software Engineering Department Riyadh12372 Saudi Arabia Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan

With the rising demand for intelligent services and privacy protection in consumer artificial intelligence (AI), federated edge learning has emerged as a beacon for privacy-preserving distributed machine learning. This non-centralized approach offers distinct data privacy advantages, making it especially suitable for applications with strict privacy policies, such as consumer-centric healthcare systems. However, consumer electronics/devices in federated edge learning might unlawfully violate model ownership by duplicating or distributing models. Another concern is that a central server, if compromised, can become a conduit for model leakage, whether for profit motives or due to external intrusions, thus exacerbating the model ownership violation. To our knowledge, few works have focused on model ownership protection for federated edge learning in the consumer-centric healthcare domain. In this paper, we introduce a federated model ownership protection (FedMOP) approach. FedMOP is a model ownership safeguard and a formidable fortress built upon two core innovations. First, FedMOP can swiftly embed and replace watermarks during local training, allowing for the accurate identification and subsequent flagging of deceitful consumer devices. Second, FedMOP ensures that the server only accesses encrypted versions of the federated model, keeping the model a secret. Extensive evaluations demonstrate the robustness and effectiveness of FedMOP. We hope that FedMOP can light the way for surmounting similar ethical challenges in the broader realm of consumer-edge AI. © 1975-2011 IEEE.

关键词： ethical AI Federated edge learning healthcare consumer electronicss model ownership protection

来源：评论

学校读者我要写书评

暂无评论

S2WAT: Image Style Transfer via Hierarchical Vision Transformer Using Strips Window Attention

arXiv

引用

arXiv 2022年

作者： Zhang, Chiyu Xu, Xiaogang Wang, Lei Dai, Zaiyan Yang, Jun Sichuan Normal University China Nanjing University of Aeronautics and Astronautics China Zhejiang Lab China Zhejiang University China Visual Computing and Virtual Reality Key Laboratory of Sichuan Provience China

Transformer's recent integration into style transfer leverages its proficiency in establishing long-range dependencies, albeit at the expense of attenuated local modeling. This paper introduces Strips Window Attention Transformer (S2WAT), a novel hierarchical vision transformer designed for style transfer. S2WAT employs attention computation in diverse window shapes to capture both short- and long-range dependencies. The merged dependencies utilize the "Attn Merge" strategy, which adaptively determines spatial weights based on their relevance to the target. Extensive experiments on representative datasets show the proposed method's effectiveness compared to state-of-the-art (SOTA) transformer-based and other approaches. The code and pre-trained models are available at https://***/AlienZhang1996/S2WAT. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Slimmable transformer with hybrid axial-attention for medical image segmentation

引用

Computers in Biology and Medicine 2024年 173卷 108370-108370页

作者： Hu, Yiyue Mu, Nan Liu, Lei Zhang, Lei Jiang, Jingfeng Li, Xiaoning College of Computer Science Sichuan Normal University Chengdu610101 China School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen518172 China Department of Biomedical Engineering Michigan Technological University HoughtonMI49931 United States Visual Computing and Virtual Reality Key Laboratory of Sichuan Sichuan Normal University Chengdu610068 China Education Big Data Collaborative Innovation Center of Sichuan 2011 Chengdu610101 China

The transformer architecture has achieved remarkable success in medical image analysis owing to its powerful capability for capturing long-range dependencies. However, due to the lack of intrinsic inductive bias in modeling visual structural information, the transformer generally requires a large-scale pre-training schedule, limiting the clinical applications over expensive small-scale medical data. To this end, we propose a slimmable transformer to explore intrinsic inductive bias via position information for medical image segmentation. Specifically, we empirically investigate how different position encoding strategies affect the prediction quality of the region of interest (ROI) and observe that ROIs are sensitive to different position encoding strategies. Motivated by this, we present a novel Hybrid Axial-Attention (HAA) that can be equipped with pixel-level spatial structure and relative position information as inductive bias. Moreover, we introduce a gating mechanism to achieve efficient feature selection and further improve the representation quality over small-scale datasets. Experiments on LGG and COVID-19 datasets prove the superiority of our method over the baseline and previous works. Internal workflow visualization with interpretability is conducted to validate our success better;the proposed slimmable transformer has the potential to be further developed into a visual software tool for improving computer-aided lesion diagnosis and treatment planning. © 2024 Elsevier Ltd

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Cross-Angle Facial Individual Verification of Giant Panda

Cross-Angle Facial Individual Verification of Giant Panda

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jiawei Wu Han Su Peng Min Mengnan He Pengcheng Wu Gai Luo Rong Hou Peng Chen College Computer Science of Sichuan Normal University Chengdu China College of Computer Science Sichuan Normal University Chengdu China and also with Visual Computing and visual reality Key Laboratory of Sichuan Province Chengdu China College of Sichuan Normal University Chengdu China Chengdu Research Base of Giant Panda Chengdu Research Base of Giant Panda Breeding Sichuan Normal University Chengdu China Chengdu Research Base of Giant Panda Breeding

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Enhancing the protection of giant pandas necessitates a precise means of verifying their individual information. With the development of deep learning technology, some individual recognition methods for giant pandas have emerged. However, these methods often neglect cross-angle facial recognition, a common occurrence in natural settings, and predominantly focus on identification rather than verification, rendering them unsuitable for wild populations of unknown individuals. Cross-angle facial verification poses novel challenges, notably feature misalignment and geometric deformation induced by varying angles, particularly in the verification process reliant on comparing feature discrepancies. To address this issue, we developed the CrossPandaFace model. This model employs a Pixel Drift Unit (PDU) to adjust feature pixels and utilizes template features generated by the Template Generation Module (TGM) as a reference to align giant pandas from different angles onto a unified template. Furthermore, Multi-scale Feature Supplement (MSFS) compensates for the potential risk of losing local features of aligned features. Experimental results show state-of-the-art performance, thus affirming the efficacy of our model for cross-angle giant panda verification.

关键词： Deep learning Deformation Face recognition Rendering (computer graphics) Protection Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Constructing intuitionistic neighborhood based on intuitionistic fuzzy sets for three-way clustering

引用

International Journal of Approximate Reasoning 2025年 186卷

作者： Yu Xie Jilin Yang Yiyu Luo Xianyong Zhang Junfang Luo Department of Computer Science Sichuan Normal University Chengdu 610101 China Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Chengdu 610000 China School of Computing and Artificial Intelligence Southwestern University of Finance and Economics Chengdu 610074 China

Three-way clustering assigns highly uncertain samples to the boundary domains, effectively addressing the problem of misclassification caused by data uncertainty. In numerical attribute information systems, neighborhood rough sets can effectively capture the indiscernibility relations between objects. However, the conventional neighborhood relation suffers from a one-size-fits-all issue due to the fixed neighborhood radius. To solve these issues, we propose an intuitionistic neighborhood and construct a corresponding three-way clustering model. Specifically, we first capture the dual nature and uncertainty of neighborhood relations through the construction of the intuitionistic neighborhood. Then we construct a three-way clustering model with dual and single evaluation functions based on intuitionistic neighborhoods. Finally, we adaptively obtain the optimal threshold pairs by maximizing the clustering effectiveness index. Experiments conducted on twelve datasets demonstrate that our proposed method outperforms baseline methods, showing superior capability in handling the inherent uncertainty in information systems.

关键词： Atanassov intuitionistic fuzzy sets Dual evaluation functions Neighborhood rough sets Three-way clustering

来源：评论

学校读者我要写书评

暂无评论

A Study on the Mechanism and Kinetic of Nitrate Reduction by the nZVI-g-C3N4/TiO2 composite under the simulated sunlight

Research Square

引用

Research Square 2021年

作者： Wei, Linyu Tian, Jing Wang, Qing Liu, Yuanyuan Yu, Yi Yang, Chun College of Chemistry and Materials Science Sichuan Normal University Chengdu610066 China Sichuan Engineering Laboratory of Livestock Manure Treatment and Recycling Chengdu140028001 China Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Sichuan Normal University Chengdu610068 China

g-C3N4/TiO2 composite has excellent photoelectric properties and is considered as a good carrier of nanoparticles. A novel composite of nZVI-g-C3N4/TiO2 was successfully synthesized through in-situ growth nZVI on the surface of g-C3N4/TiO2 with liquid phase reduction method. The composite was characterized by TEM, XRD, EDS and evaluated its nitrate removal efficiency. The effects of composite dosage, solution initial pH and HCOOH concentration on nitrate reduction were investigated. The results showed that nitrate was rapidly reduced by nZVI-g-C3N4/TiO2 composite. The dosage of 4 g/L nZVI-g-C3N4/TiO2 composite and 3.0 mM of HCOOH concentration was more suitable for nitrate reduction. Solution initial pH had little impact on the nitrate reduction efficiency, but affected the proportion of the nitrate reduction products. The mechanism of nitrate reduction in the nZVI-gC3N4/TiO2/HCOOH-Xe-lamp system was proposed. The nZVI-gC3N4/TiO2 composite could be considered as a viable and promising technology for water pollution remediation. © 2021, CC BY.

关键词： Nitrates

来源：评论

学校读者我要写书评

暂无评论

A study on hair density analysis for androgenic hair pattern of low-resolution leg images

A study on hair density analysis for androgenic hair pattern...

引用

International Conference on Intelligent computing, Communication and Devices, ICCD 2017

作者： Su, Han School of Computer Science Sichuan Normal University Chengdu610101 China Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Chengdu610066 China

ISBN: (纸本)9789811089435

Androgenic hair which is also named as body hair can be used for identifying criminals and victims. It is a new soft biometric trait. Different with skin mark, tattoo, blood vessels, and so on, androgenic hair is suitable for low-resolution images. Recently, some researches proved that the androgenic hair pattern extracted from low-resolution images also has valuable discriminative power. In the features of androgenic hair pattern that used for identification, hair density which did not separately be described in the previous works is an important feature. This paper focuses on the hair density, describes, and extracts density feature explicitly. The different grade densities are classified, and the density difference is captured by the density descriptors. The three density grades which are called high density, medium density, and low density are classified by the hair density classifier. In this paper, the grades of different densities are tried to use for modifying the affect of the defect in dynamic grid system. The performance of hair density is tested on forensic skin image database. The experiment result shows that the method is efficient. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Retraction-based first-order feasible methods for difference-of-convex programs with smooth inequality and simple geometric constraints

arXiv

引用

arXiv 2021年

作者： Zhang, Yongle Li, Guoyin Pong, Ting Kei Xu, Shiqi Department of Mathematics Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Sichuan Normal University Chengdu China Department of Applied Mathematics University of New South Wales Sydney Australia Department of Applied Mathematics The Hong Kong Polytechnic University Hong Kong Department of Mathematics Sichuan Normal University Chengdu China

In this paper, we propose first-order feasible methods for difference-of-convex (DC) programs with smooth inequality and simple geometric constraints. Our strategy for maintaining feasibility of the iterates is based on a "retraction" idea adapted from the literature of manifold optimization. When the constraints are convex, we establish the global subsequential convergence of the sequence generated by our algorithm under strict feasibility condition, and analyze its convergence rate when the objective is in addition convex according to the Kurdyka-Lojasiewicz (KL) exponent of the extended objective (i.e., sum of the objective and the indicator function of the constraint set). We also show that the extended objective of a large class of Euclidean norm (and more generally, group LASSO penalty) regularized convex optimization problems is a KL function with exponent 1/2;consequently, our algorithm is locally linearly convergent when applied to these problems. We then extend our method to solve DC programs with a single specially structured nonconvex constraint. Finally, we discuss how our algorithms can be applied to solve two concrete optimization problems, namely, group-structured compressed sensing problems with Gaussian measurement noise and compressed sensing problems with Cauchy measurement noise, and illustrate the empirical performance of our algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Frank-Wolfe-type methods for a class of nonconvex inequality-constrained problems

arXiv

引用

arXiv 2021年

作者： Zeng, Liaoyuan Zhang, Yongle Li, Guoyin Pong, Ting Kei Wang, Xiaozhou College of Science Zhejiang University of Technology Zhejiang Hangzhou China School of Mathematical Sciences Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Sichuan Normal University Sichuan Chengdu China Department of Applied Mathematics University of New South Wales Sydney Australia Department of Applied Mathematics The Hong Kong Polytechnic University Hong Kong

The Frank-Wolfe (FW) method, which implements efficient linear oracles that minimize linear approximations of the objective function over a fixed compact convex set, has recently received much attention in the optimization and machine learning literature. In this paper, we propose a new FW-type method for minimizing a smooth function over a compact set defined as the level set of a single difference-of-convex function, based on new generalized linear-optimization oracles (LO). We show that these LOs can be computed efficiently with closed-form solutions in some important optimization models that arise in compressed sensing and machine learning. In addition, under a mild strict feasibility condition, we establish the subsequential convergence of our nonconvex FW-type method. Since the feasible region of our generalized LO typically changes from iteration to iteration, our convergence analysis is completely different from those existing works in the literature on FW-type methods that deal with fixed feasible regions among subproblems. Finally, motivated by the away steps for accelerating FW-type methods for convex problems, we further design an away-step oracle to supplement our nonconvex FW-type method, and establish subsequential convergence of this variant. Numerical results on the matrix completion problem with standard datasets are presented to demonstrate the efficiency of the proposed FW-type method and its away-step variant. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Learning an Effective Charging Scheme for Mobile Devices

Learning an Effective Charging Scheme for Mobile Devices

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Tang Liu Baijun Wu Wenzheng Xu Xianbo Cao Jian Peng Hongyi Wu Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Sichuan Normal University Chengdu China University of Louisiana at Lafayette Lafayette LA USA College of Computer Science Sichuan University Chengdu China Center for Cybersecurity Education and Research Dominion University Norfolk VA USA

ISBN: (数字)9781728168760

ISBN: (纸本)9781728168777

Wireless charging has been demonstrated as a promising technology for prolonging device operational lifetimes in Wireless Rechargeable Networks (WRNs). To schedule a mobile charger to move along a predesigned trajectory to charge devices, most existing studies assume that the precise location information of devices is already known. Unfortunately, this assumption does not always hold in real mobile application, because the activities of vast majority of mobile devices carried by mobile agents appear dynamic and random. To the best of our knowledge, this is the first work to study how to wirelessly charge mobile devices with non-deterministic mobility. We aim to provide effective charging service to them, subject to the energy capacity of the mobile charger. Then, we formalize the effective charging problem as a charging reward maximization problem (CRMP), where the amount of reward obtained by charging a de-vice is inversely proportional to the residual lifetime of the device. To derive an effective charging heuristic, an algorithm based on Reinforcement Learning (RL) is proposed. The evaluation results show that the RL-based charging algorithm achieves excellent charging effectiveness. We further interpret the learned heuristic to gain deep and valuable insights into the design options.

关键词： Mobile handsets Heuristic algorithms Batteries Trajectory Wireless communication Energy consumption Wireless sensor networks

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：