检索结果-内蒙古大学图书馆

IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)

作者： Zhihao Du Yike Li Chao Chen Zheng Wang Shenzhen Institute of Advanced Technology ChineseAcademy of Sciences Shenzhen China School of Software Engineering University of Science and Technology of China

Transformer-based models have achieved state-of-the art performance in many Artificial Intelligence (AI) tasks. The core component of the transformer is the attention mechanism, which includes computation-intensive operators-such as MatMul and Linear-raising demand for hardware support. Many Institute, and researchers have proposed their hardware acceleration methods in recent years. However, most of these works mainly focus on algorithm optimization and hardware performance. Little attention has been paid to the variable sequence lengths in the attention mechanism. In the hardware design, the variability of sequence length brings a challenge to the load-store unit and on-chip data movement. In this work, we first propose a hardware-friendly fine-grained padding method aiming to handle the variability of sequence length in scaled dot-product attention. Then, a hardware architecture named AttenTPU is proposed using the padding method. The experimental results indicate that compared to the CPU and GPU platform, our accelerator achieves speed-ups of $3.43\times$ and $1.41\times$ , respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy Enhanced Mobile User Authentication Method Using Motion Sensors

引用

Computer Modeling in engineering & Sciences 2024年第3期138卷 3013-3032页

作者： Chunlin Xiong Zhengqiu Weng Jia Liu Liang Gu Fayez Alqahtani Amr Gafar Pradip Kumar Sharma Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518052China Sangfor Technologies Inc. Shenzhen518055China School of Data Science and Artificial Intelligence Wenzhou University of TechnologyWenzhou325035China College of Computer Science&Technology Zhejiang University of TechnologyHangzhou310023China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Math&Computer Science Department Faculty of ScienceMenofia UniversityShebin El-KomEgypt Computing Science Department University of AberdeenAberdeenUK

With the development of hardware devices and the upgrading of smartphones,a large number of users save privacy-related information in mobile devices,mainly smartphones,which puts forward higher demands on the protection of mobile users’privacy *** present,mobile user authenticationmethods based on humancomputer interaction have been extensively studied due to their advantages of high precision and non-perception,but there are still shortcomings such as low data collection efficiency,untrustworthy participating nodes,and lack of *** this end,this paper proposes a privacy-enhanced mobile user authentication method with motion sensors,which mainly includes:(1)Construct a smart contract-based private chain and federated learning to improve the data collection efficiency of mobile user authentication,reduce the probability of the model being bypassed by attackers,and reduce the overhead of data centralized processing and the risk of privacy leakage;(2)Use certificateless encryption to realize the authentication of the device to ensure the credibility of the client nodes participating in the calculation;(3)Combine Variational Mode Decomposition(VMD)and Long Short-TermMemory(LSTM)to analyze and model the motion sensor data of mobile devices to improve the accuracy of model *** experimental results on the real environment dataset of 1513 people show that themethod proposed in this paper can effectively resist poisoning attacks while ensuring the accuracy and efficiency of mobile user authentication.

关键词： Mobile authentication blockchain federated learning smart contract certificateless encryption VMD LSTM

来源：评论

学校读者我要写书评

暂无评论

HistoDX: Revolutionizing Breast Cancer Diagnosis Through advanced Imaging Techniques

引用

IEEE Access 2025年 13卷 94416-94436页

作者： Arshad, Wishal Masood, Tehreem Shahzad, H.M. Ahmed, Hassan A. Ahmed, Syed Hamza Khushi, Hafiz Muhammad Tayyab University of Central Punjab Faculty of Software Engineering and Information Technology Lahore54000 Pakistan Superior University Faculty of Computer Science and Information Technology Lahore54000 Pakistan Superior University Department of Software Engineering Lahore54000 Pakistan Cleveland State University Monte Ahuja College of Business Department of Information Systems ClevelandOH44114 United States

Breast cancer is the second leading cause of mortality among women worldwide, highlighting the need for efficient histopathology-based screening methods for early diagnosis. This study introduces HistoDX, a deep learning framework to classify Invasive Ductal Carcinoma (IDC) using 277,524 histopathology image patches (50x50 pixels) from Paul Mooney's IDC dataset on Kaggle, comprising No Cancer and IDC(+) classes. HistoDX employs a preprocessing pipeline with normalization, data augmentation, and class balancing via oversampling and weighted loss to address the class imbalance. A customized convolutional neural network, built on EfficientNetV2-B3 with additional layers, achieves 97% accuracy and a 0.91 ROC-AUC score on the test set. Validation on BreakHis (97% accuracy) and BACH (90% accuracy) datasets confirm generalizability, though detecting minority IDC(+) cases remains challenging. Low training and test losses underscore reliability. HistoDX empowers pathologists by enhancing diagnostic efficiency and minimizing subjectivity through effective class imbalance mitigation. Its robust performance across diverse datasets like BreakHis and BACH suggests readiness for clinical integration. Future research into advanced augmentation techniques, ensemble models, and whole-slide image analysis could further optimize accuracy, sensitivity, and scalability, paving the way for broader adoption in precision oncology. © 2013 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

VPNeXt: Rethinking Dense Decoding for Plain Vision Transformer

arXiv

引用

arXiv 2025年

作者： Tang, Xikai Huang, Ye Yin, Guangqiang Duan, Lixin School of Information and Software Engineering University of Electronic Science and Technology of China China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China 518000 China

We present VPNeXt, a new and simple model for the Plain Vision Transformer (ViT). Unlike the many related studies that share the same homogeneous paradigms, VPNeXt offers a fresh perspective on dense representation based on ViT. In more detail, the proposed VPNeXt addressed two concerns about the existing paradigm: (1) Is it necessary to use a complex Transformer Mask Decoder architecture to obtain good representations? (2) Does the Plain ViT really need to depend on the mock pyramid feature for upsampling? For (1), we investigated the potential underlying reasons that contributed to the effectiveness of the Transformer Decoder and introduced the Visual Context Replay (VCR) to achieve similar effects efficiently. For (2), we introduced the ViTUp module. This module fully utilizes the previously overlooked ViT real pyramid feature to achieve better upsampling results compared to the earlier mock pyramid feature. This represents the first instance of such functionality in the field of semantic segmentation for Plain ViT. We performed ablation studies on related modules to verify their effectiveness gradually. We conducted relevant comparative experiments and visualizations to show that VPNeXt achieved state-of-the-art performance with a simple and effective design. Moreover, the proposed VPNeXt significantly exceeded the long-established mIoU wall/barrier of the VOC2012 dataset, setting a new state-of-the-art by a large margin, which also stands as the largest improvement since 2015. © 2025, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Influence of Structural Units on Vulnerability of systems with Distinct Protection Approaches

Influence of Structural Units on Vulnerability of Systems wi...

引用

Euromicro Symposium on Digital System Design

作者： Ján Mach Lukáš Kohútka Pavel Čičak Institute of Computer Engineering and Applied Informatics Slovak University of Technology Bratislava Slovakia Institute of Informatics Information Systems and Software Engineering Slovak University of Technology Bratislava Slovakia

ISBN: (数字)9798350380385

ISBN: (纸本)9798350380392

Mission/safety-critical applications rely on the dependability of their semiconductor control systems. The lockstepping is state-of-the-art when it comes to their protection. This paper compares the dual/triple lockstep systems with the Hardisc, which features microarchitecture-level protection. For a fair comparison, each system is based on the same architecture and integrates protection against bit-flips in memory and transient faults in the bus. We analyse how individual structures of the system affect the vulnerability of a system to faults. Our fault injection methodology combines pre-synthesis simulation with synthesis data to scale the fault rate of the structures according to their size. The results show that the Hardisc can withstand fault rates orders of magnitude higher than the dual-core lockstep system while preserving the same area and power consumption. It comes with a 5% frequency penalty. The pipeline logic has the most significant impact on the vulnerability of the lockstep system. On the other hand, the ECC-protected register file constraints the maximum failure rate the Hardisc can withstand due to fault accumulation during specific program sections.

关键词： Fault tolerance Power demand Microarchitecture Digital systems Pipelines Fault tolerant systems Registers Logic Protection Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Interface Protection Against Transient Faults

Interface Protection Against Transient Faults

引用

IEEE Design and Diagnostics of Electronic Circuits and systems (DDECS)

作者： Ján Mach Lukáš Kohútka Pavel Čičák Institute of Computer Engineering and Applied Informatics Slovak University of Technology Bratislava Slovakia Institute of Informatics Information Systems and Software Engineering Slovak University of Technology Bratislava Slovakia

Increasing bus frequency to fulfill the performance requirements of dependable applications may increase the susceptibility of the system to transient faults. This paper describes an integration of protection against transient bus faults into the interface of the Hardisc RISC-V core. The protection is based on information redundancy with spatial redundancy features. It enables uninterrupted execution in the presence of transient faults and provides a hardware-software interface for its reporting. The benchmarking results indicate that most of the applications will be impacted minimally. The protection has a negligible impact on the maximal frequency and 8% area and power consumption overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards an Automated Process for Adaptive Modelling of Orthoses and Shoe Insoles in Additive Manufacturing 12

Towards an Automated Process for Adaptive Modelling of Ortho...

引用

12th International Workshop on Innovative Simulation for Health Care, IWISH 2023

作者： Zwettler, Gerald A. Trixner, Martin Schartmüller, Clemens Bauernfeind, Sophie Stockinger, Thomas Praschl, Christoph Research Group Advanced Information Systems and Technology Research and Development Department University of Applied Sciences Upper Austria Department of Software Engineering School of Informatics Communications and Media University of Applied Sciences Upper Austria Granitweg 1 Kirchschlag bei Linz4202 Austria Pulvermühlstrasse 3 Linz4040 Austria

ISBN: (纸本)9788885741966

Although orthopedics is becoming increasingly important as a medical domain, especially in emerging countries, the level of automation is still marginal and hardly any Industry 4.0 paradigms have been implemented. In this scientific work, solution concepts for holistic process automation in orthopedics are introduced so that prosthetic covers and orthoses for different body regions can be automated by using AI and evaluated with sensor networks. In this process, body scan models are adapted to the conditions of the anatomy or prosthesis models, so that stability as well as fitting accuracy are given in comparison with the other half of the body. Automation in the field of orthopedics leads not only to a significant reduction in costs but can also help to close the research gap regarding objectifiability of results. The first partial aspects have already been successfully implemented for leg prostheses, arm prostheses and shoe insoles with the aid of machine learning processes and physical models for elastic form fitting. As soon as the overall process has been realized, the applicability will be validated in the following year of the project by means of clinical studies and evaluated by utilizing sensor networks for pressure and temperature measurements. © 2023 The Authors.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Algorithm For MRI Brain Alzheimer's Disease Prediction

Hybrid Deep Learning Algorithm For MRI Brain Alzheimer's Dis...

引用

2023 International Conference on Energy, Materials and Communication engineering, ICEMCE 2023

作者： Karthikeyan, D. Nivasini, R. Raja, Kiruba Thangam Madhivadhani, D. Sivakumar, B. Krishna Priya, A.T.R. Srm Institute of Science and Technology Department of Electrical and Electronics Engineering Kattankulathur Chennai India Iitm Research Park Guvi Geek Networks Tamilnadu Chennai India Vit University School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Vellore India Kings Engineering College Department of Electronics and Communication Engineering Sriperumbudur Chennai India Rohini College of Engineering and Technology Department of Computer Science and Engineering Kanyakumari India

ISBN: (纸本)9798350393378

Magnetic resonance imaging (MRI) has been used to study the structural makeup of the brain and analyse several neurological disorders and diseased areas. For the adoption of preventative measures, early recognition of Alzheimer's disease (AD) patients is essential. Here, a thorough inspection of the tissue arrangements obtained by MRI images of Outcome and Assessment Information (OASIS) dataset enables an exact characterization of certain brain diseases. There have been a number of division techniques for diagnosing AD that range in complexity. Compassion has been tested by deep learning techniques used to segment the structure of the brain and classify AD because they have the potential to uncover important information from vast amounts of data. In this paper the deep learning technique of Hybrid Dragonfly based GWO convolutional Neural Network (CNN) is achieved promising result for the diagnosis of AD. At image preprocessing wiener filter is used for removing the additive noises and the Gray Level Co-Occurrence Matrix (GLCM) extraction is implemented for texture analyzing. As a result, hybrid deep learning methods of CNN has the accuracy as 90% and the result of the image prediction are presented in this paper. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Lockstep Vs Microarchitecture: A Comparison

Lockstep Vs Microarchitecture: A Comparison

引用

IEEE International SOC Conference

ISBN: (数字)9798350377569

ISBN: (纸本)9798350377576

Safety/mission-critical applications require high dependability of the control systems. Their state-of-the-art protection approach is a system-level lockstep. This paper compares the system-level dual and triple lockstep technique to the microarchitecture-level protection of the Hardisc RISC-V core. For a fair comparison, each system is based on the same core(s) and integrates protection against bit-flips in memory and transient faults in the bus. We propose a fault injection methodology, combining pre-synthesis simulation with synthesis data to analyse the vulnerability of a system to faults. The fault injection campaigns show that the Hardisc can withstand fault rates orders of magnitude higher than the dual-core lockstep system while preserving the same area and power consumption. It comes with a 5% frequency penalty. We have shown that system failures are more frequent once the fault rate reaches an application-specific threshold (one fault in 100 clock cycles).

关键词： Fault tolerance Microarchitecture Power demand Event detection Fault tolerant systems Registers System-on-chip Protection Transient analysis Clocks

来源：评论

学校读者我要写书评

暂无评论

Recognition of Fire Situation Using Graph Convolutional Network Model 15th

Recognition of Fire Situation Using Graph Convolutional Netw...

引用

15th International Conference on Computer Science and its Applications, CSA 2023 and 17th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2023

作者： Kim, Si Jin Park, Ji Su Kang, Jungho Shon, Jin Gon Advanced Convergence Technology Laboratory Korea National Open University Seoul Korea Republic of Department of Computer Science and Engineering Jeonju University Jeonju-Si Korea Republic of Department of Software Engineering Baewha Woman University Seoul Korea Republic of Department of Computer Science Korea National Open University Seoul Korea Republic of

ISBN: (纸本)9789819724468

Fires cause a lot of casualties and economic losses. In order to prevent fire accidents in advance, it is necessary to find out the cause of the fire. Existing fire alarm systems detected fires with temperature, smoke, and flame sensors, but could not distinguish the cause of the fire. In this paper, to solve this problem, the recognition of fire situation was tested using the GCN model. The fire dataset used in the experiment is a fire dataset composed of causes such as boxes, clothing, and electricity. The accuracy of 93.44% was confirmed as a result of the learning experiment with the GCN model, a graph-based deep learning model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Premixed flames

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：