检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Yao Ye, Zesheng Wang, Rui Li, Binghao Sheng, Quan Z. Yao, Lina School of Computing Macquarie University Sydney Australia School of Computer Science and Engineering University of New South Wales Sydney Australia College of Information Science and Engineering Northeastern University Shenyang China School of Minerals and Energy Resources Engineering University of New South Wales Sydney Australia Data 61 CSIRO Sydney Australia

Tremendous efforts have been put forth on predicting pedestrian trajectory with generative models to accommodate uncertainty and multi-modality in human behaviors. An individual’s inherent uncertainty, e.g., change of destination, can be masked by complex patterns resulting from the movements of interacting pedestrians. However, latent variable-based generative models often entangle such uncertainty with complexity, leading to limited either latent expressivity or predictive diversity. In this work, we propose to separately model these two factors by implicitly deriving a flexible latent representation to capture intricate pedestrian movements, while integrating predictive uncertainty of individuals with explicit bivariate Gaussian mixture densities over their future locations. More specifically, we present a model-agnostic uncertainty-aware pedestrian trajectory prediction framework, parameterizing sufficient statistics for the mixture of Gaussians that jointly comprise the multi-modal trajectories. We further estimate these parameters of interest by approximating a denoising process that progressively recovers pedestrian movements from noise. Unlike previous studies, we translate the predictive stochasticity to explicit distributions, allowing it to readily generate plausible future trajectories indicating individuals’ self-uncertainty. Moreover, our framework is compatible with different neural net architectures. We empirically show the performance gains over state-of-the-art even with lighter backbones, across most scenes on two public benchmarks. Copyright © 2023, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Deep learning and blockchain-based secure authentication protocol for privacy protection in cloud environments

引用

Peer-to-Peer Networking and Applications 2025年第4期18卷 1-27页

作者： Subbarayan, Kalaiselvi Garikapati, Bindu Chinnavel, Sivakumar Sarveshwaran, Velliangiri Department of Computer Technology Kongu Engineering College Erode India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur India School of Computing Department of Data Science Mohan Babu University Tirupati India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur India National Chung Cheng University Chiyai Taiwan (R.O.C.)

Cloud-based healthcare computing has significantly transformed the healthcare landscape. Key advantages include the scalability of services and the flexibility to adjust data capacity as needed. However, this evolution also introduces challenges, such as data breaches, insider threats, phishing attacks, and the use of weak passwords. To overcome these issues, an authentication technique based on blockchain is introduced to ensure the privacy protection of medical data transmitted over the cloud. Here, data authentication is performed by five entities that include patient, cloud server, doctor, Trusted Authority (TA) and blockchain. Then, data augmentation is performed using the processes, such as initialization, registration, key generation. authentication, data protection, data upload, data sharing and data decryption. Further, data is encrypted by the Advanced Encryption Standard (AES) method, which is based on a secret key generated by Deep Maxout Network (DMN). Additionally, KeyGenDMN outperformed the existing technique with a value of 1.533 sec, 41.926 Mb, 3.504 sec, 0.003, 0.770, and 0.535J for computational time, memory usage, latency, throughput, packet loss, reliability metrics, and energy consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diabetes Mellitus Type 2 data Sharing System Based on Blockchain and Attribute-Encryption

Diabetes Mellitus Type 2 Data Sharing System Based on Blockc...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Weiqi Dai Zhenhui Lu Xia Xie Duoqiang Wang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Hainan University Haikou China

Medical data sharing can improve the quality of medical care and promote progress in the field of public health. However, medical data has high confidentiality and complexity. Taking the clinical diagnosis and treatment data of Diabetes Mellitus Type 2 (T2DM) in medical treatment as an example, T2DM data often has the phenomenon of "multi-disease coexistence" and is insecure and inaccurate in the process of sharing. Based on Blockchain and Attribute- Encryption (ABE), we propose a T2DM data sharing system to solve the above problems. An Attribute-Encryption algorithm T2DM-CP-ABE is proposed to solve the problem of excessive sharing granularity. T2DM-CP-ABE, combined with the medical data contribution module, takes the contribution factor as an important consideration, to stimulate the power of T2DM data sharing and promote the development of national diabetes prevention. Based on the Blockchain, a medical data attribute authorization model is proposed, which provides a credible solution for multiple hospitals to realize medical data attribute authorization, and realizes the clinical diagnosis and treatment data sharing of T2DM among doctors. Based on Blockchain and ABE technology, a data sharing system for T2DM has been implemented on the Fabric platform. The result shows that the average time for the system to complete a single sharing is less than 1 second.

关键词： Authorization Hospitals Fabrics Blockchains Diabetes Encryption Security

来源：评论

学校读者我要写书评

暂无评论

Automated Detection and Segmentation of Glioblastoma in MRI Using Multi-Level Diffusion Transformer U-Net

Automated Detection and Segmentation of Glioblastoma in MRI ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Anum Masood Usman Naseem Junaid Rashid Imran Razzak Department of Radiology Harvard Medical School Harvard University Boston U.S.A. Institute of Neurosciences and Medicine (INM) Forschungszentrum Juelich Juelich Germany School of Computing Macquarie University Sydney Australia Department of Data Science Sejong University Korea School of Computer Science and Engineering UNSW Sydney Australia

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Detecting malignant tumors at an early stage is crucial for effective treatment and an improved prognosis of brain cancer. Radiologists use MRI imaging modality to detect and diagnose glioblastoma. For efficient detection, numerous deeplearning methods have been proposed in the past decade. Detecting brain tumors in MR images is challenging owing to the heterogeneity in anatomical structures across patients, and difficulties posed by low contrast, inhomogeneous intensity levels, and artifacts. In this paper, we proposed a multi-level Diffusion Transformer U-Net (mDT-UNet) with a modified cross-attention module. Our model extracts features from both global and local levels of the MR images and manual segmentations providing a wider range of contextual information. Our proposed model attained an average accuracy of 95% on the BraTS 2020 dataset whereas U-Net achieved 81% and Swin Transformer achieved 86% accuracy. In addition, we evaluated our model on various benchmark datasets; CPM-RadPath, UCSF PDGM, EGD, and IvyGAP. With appropriate pre-training on large medical datasets, our model can be optimized for various medical image segmentation tasks.

关键词： Image segmentation Accuracy Sensitivity Magnetic resonance imaging Biological system modeling Benchmark testing Transformers

来源：评论

学校读者我要写书评

暂无评论

MAST: Video Polyp Segmentation with a Mixture-Attention Siamese Transformer

arXiv

引用

arXiv 2024年

作者： Chen, Geng Yang, Junqing Pu, Xiaozhou Ji, Ge-Peng Xiong, Huan Pan, Yongsheng Cui, Hengfei Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Computing Australian National University Canberra Australia Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Harbin Institute of Technology China

Accurate segmentation of polyps from colonoscopy videos is of great significance to polyp treatment and early prevention of colorectal cancer. However, it is challenging due to the difficulties associated with modelling long-range spatio-temporal relationships within a colonoscopy video. In this paper, we address this challenging task with a novel Mixture-Attention Siamese Transformer (MAST), which explicitly models the long-range spatio-temporal relationships with a mixture-attention mechanism for accurate polyp segmentation. Specifically, we first construct a Siamese transformer architecture to jointly encode paired video frames for their feature representations. We then design a mixture-attention module to exploit the intra-frame and inter-frame correlations, enhancing the features with rich spatio-temporal relationships. Finally, the enhanced features are fed to two parallel decoders for predicting the segmentation maps. To the best of our knowledge, our MAST is the first transformer model dedicated to video polyp segmentation. Extensive experiments on the large-scale SUN-SEG benchmark demonstrate the superior performance of MAST in comparison with the cutting-edge competitors. Our code is publicly available at https://***/Junqing-Yang/MAST. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training

arXiv

引用

arXiv 2023年

作者： Chen, Chang Li, Min Wu, Zhihua Yu, Dianhai Yang, Chao Center for Data Science Peking University China School of Mathematical Sciences Peking University China National Engineering Laboratory for Big Data Analysis and Applications Peking University China Baidu Inc China Institute for Computing and Digital Economy Peking University China

Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system optimization perspective, existing MoE dispatch patterns are still not able to fully exploit the underlying heterogeneous network environments. In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the network topology. Based on communication modeling, we abstract the dispatch problem into an optimization objective and obtain the approximate dispatch pattern under different topologies. On top of that, we design a topology-aware auxiliary loss, which can adaptively route the data to fit in the underlying topology without sacrificing the model accuracy. Experiments show that TA-MoE can substantially outperform its counterparts on various hardware and model configurations, with roughly 1.01x-1.61x, 1.01x-4.77x, 1.25x-1.54x improvements over the popular DeepSpeed-MoE, FastMoE and FasterMoE systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Federated-Learning-Based Wireless Traffic Prediction

Federated-Learning-Based Wireless Traffic Prediction

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Feng Li Xiaona Chen Kwok-Yan Lam Bowen Shen Li Wang School of Information and Electronic Engineering Zhejiang Gongshang University Hangzhou China Strategic Centre for Research in Privacy-Preserving Technologies & Systems Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore College of Marine Electrical Engineering Dalian Maritime University Dalian China

ISBN: (数字)9798331507022

ISBN: (纸本)9798331507039

Accurate traffic prediction is crucial for enhancing the performance of intelligent cellular networks, as it directly impacts the effective allocation of network resources and user satisfaction. The instability and dynamics of traffic data pose challenges to centralized prediction methods. These methods are limited in prediction accuracy and may lead to issues concerning data privacy breaches and response delays. Furthermore, traditional Federated Learning (FL) typically employs a simple averaging strategy during model aggregation, which does not consider the heterogeneity of client data, thereby affecting the generalization performance of the global model. Therefore, this study proposes a wireless traffic prediction model that combines FL, Long Short-Term Memory (LSTM), and Kolmogorov-Arnold Networks (KAN). The aim is to enhance prediction accuracy while ensuring data privacy. The model leverages edge computing and FL techniques, enabling multiple edge devices to train LSTM models locally. By integrating KAN to explore the inherent complexity of traffic data, it enhances the model's adaptability. Furthermore, the FedNova model is introduced, which thoroughly considers the heterogeneity of data among devices and optimizes the process of updating model parameters. The extensive experimental results conducted on the Milano real dataset demonstrate that the FedNova-LSTM-KAN model exhibits significant advantages compared to existing centralized and FL methods when dealing with uneven client traffic data.

关键词： Wireless communication Adaptation models data privacy Accuracy Federated learning Computational modeling Predictive models Prediction algorithms data models Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories 25

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness...

引用

34th ACM Web Conference, WWW 2025

作者： Wang, Tianlong Jiao, Xianfeng Zhu, Yinghao Chen, Zhongzhi He, Yifan Chu, Xu Gao, Junyi Wang, Yasha Ma, Liantao School of Software and Microelectronics Peking University Beijing China Key Laboratory of High Confidence Software Technologies Ministry of Education Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Beihang University Beijing China Center on Frontiers of Computing Studies Peking University Beijing China Centre for Medical Informatics University of Edinburgh Edinburgh United Kingdom Health Data Research UK London United Kingdom Key Laboratory of High Confidence Software Technologies Ministry of Education National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (纸本)9798400712746

Recent studies have indicated that Large Language Models (LLMs) harbor an inherent understanding of truthfulness, yet often fail to consistently express it and generate false statements. This gap between "knowing" and "telling" poses a challenge for ensuring the truthfulness of generated content. Inspired by recent work on the practice of encoding human-interpretable concepts linearly within large language models, we treat truthfulness as a specially linearly encoded concept within LLMs, and introduce Adaptive Activation Steering (ACT), a tuning-free method that adaptively shifts LLM’s activations in the "truthful" direction during inference. ACT addresses diverse categories of hallucinations by utilizing diverse truthfulness-related steering vectors and adjusting the steering intensity adaptively. Applied as an add-on across various models, ACT significantly improves truthfulness in LLaMA (↑ 142%), LLaMA2 (↑ 24%), Alpaca (↑ 36%), Vicuna (↑ 28%), LLaMA2-Chat (↑ 19%), and LLaMA3(↑ 34%). Furthermore, we verify ACT’s scalability across larger models (13B, 33B, 65B), underscoring the adaptability of ACT to large-scale language models. © 2025 Copyright held by the owner/author(s).

关键词： hallucination

来源：评论

学校读者我要写书评

暂无评论

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning 39

Improving Complex Reasoning over Knowledge Graph with Logic-...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xia, Tianle Ding, Liang Wan, Guojia Zhan, Yibing Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia JD Explore Academy College of Computing and Data Science Nanyang Technological University 639798 Singapore

ISBN: (纸本)157735897X

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging task. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements (brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A comparative study of solving the surface area of solid figures in dynamic geometry system 16

A comparative study of solving the surface area of solid fig...

引用

16th IEEE International Conference on Computer Science and Education, ICCSE 2021

作者： Chen, Ningxin Guan, Hao Wang, Ying Chen, Ruxian Cai, Ruiqi Zhang, Chuanjun Institute of Computing Science and Technology Guangzhou University Guangzhou China Institute of Guangzhou Software Engineering Guangzhou China Guizhou Education University School of Mathematics and Big Data Guiyang China

ISBN: (纸本)9781665414685

As an important part of geometry, solid figures is difficult for learning and teaching. Three-dimensional dynamic geometry system(3D DGS) is significant to assist the teaching of solid figures. Solid figures can be edited and modified effectively in 3D DGS. 3D DGS provides rich functions such as viewpoint transformation, animation, text, etc., which display dynamic geometric figures more clearly and provide a vivid teaching situation in symbolic-graphic combination. We use Cabri 3D, GeoGebra and Netpad to assist in solving the problem of solid geometric surface area, and compare the pros and cons of the functions fo the three 3D DGS. We focus on how Netpad assists users in constructing and calculating the surface area of solid figures. © 2021 IEEE.

关键词： Geometry

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：