检索结果-内蒙古大学图书馆

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Kalyan Chakravarthy, N.S. Balapanur, Mouli Chandra Pandian, Arun Nambi Pulikanti, Jyothi Prasad, D. Syed Masood, Jafar Ali Ibrahim High-Performance Computing Research Laboratory QIS College of Engineering and Technology Andhra Pradesh Ongole India Department of Internet of Things School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798400709586

The demand for high-performance hardware solutions for machine learning tasks is growing as medical imaging evolves. In this paper, we will focus on the latest hardware advanced technologies: GPUs, TPUs and FPGAs that can be used for image processing optimization in medical imaging such as brain tumor segmentation or chest X-ray classification. We test these devices on the BraTS and ChestX-ray14 datasets to show how running models quicker increases diagnostic performance. The study offers a comprehensive performance and energy efficiency evaluation of all the considered hardware solutions when training deep learning models for medical imaging, providing clinical guidelines to choose appropriate new-generation accelerators before engaging in expensive leasing contracts. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： GPUS

来源：评论

学校读者我要写书评

暂无评论

kQUIC: A Kernel-Based Quick UDP internet Connections (QUIC) Transport for IoT

引用

IEEE Access 2025年 13卷 100392-100404页

作者： Puneet Kumar Behnam Dezfouli Department of Computer Science and Engineering Internet of Things Research Laboratory Santa Clara University Santa Clara CA USA

To address the shortcomings of TCP, the IETF has standardized QUIC, a new userspace transport protocol. Despite its benefits, the implementation of QUIC in the userspace introduces significant processing overhead, which makes it less suitable for IoT devices. According to our empirical analyses, as the packet loss rate increases from 0% to 2.5%, the data copying overhead between the kernel and userspace increases by 26% with QUIC, whereas TCP experiences no additional overhead. In this paper, we identify and study the overhead associated with QUIC and introduce an enhanced implementation called kQUIC, designed to enhance the protocol for IoT applications. kQUIC tackles two primary shortcomings of QUIC. First, it reduces the overhead of system calls by implementing QUIC within the kernel, as opposed to the traditional userspace implementation. Second, kQUIC enables multiple applications on an IoT device to multiplex their data through a single underlying UDP pipeline, thereby reducing transport-layer header overhead. Our analyses and empirical evaluations demonstrate that kQUIC outperforms both TCP and QUIC in terms of throughput and processor utilization. For example, in a single-application scenario with a 2.5% packet loss rate, kQUIC achieves 13.2% and 29.5% higher throughput than TCP and QUIC, respectively. Under the same conditions, with an application message size of 1400 bytes, kQUIC exhibits 49.76% lower processor utilization than QUIC and 27.41% lower than TCP. kQUIC’s application multiplexing feature further enhances throughput and reduces overall processor usage in multi-processor and multi-application scenarios across all packet loss rates and message sizes.

关键词： internet of things Sockets Kernel Switches Context Servers Packet loss Multiplexing Throughput Transport protocols

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Transfer Multi-task Learning Approach for Scene Classification 27th

Hierarchical Transfer Multi-task Learning Approach for Scen...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Khoshkangini, Reza Tajgardan, Mohsen Jamali, Mahtab Ljungqvist, Martin Georg Mihailescu, Radu-Casian Davidsson, Paul Internet of Things and People Research Center Department of Computer Science and Media Technology Malmö University Malmö Sweden Faculty of Electrical and Computer Engineering Qom University of Technology Qom Iran Axis Communications AB Lund Sweden

ISBN: (纸本)9783031781063

This paper presents a novel Hierarchical Transfer and Multi-task Learning (HTMTL) approach designed to substantially improve the performance of scene classification networks by leveraging the collective influence of diverse scene types. HTMTL is distinguished by its ability to capture the interaction between various scene types, recognizing how context information from one scene category can enhance the classification performance of another. Our method, when applied to the Places365 dataset, demonstrates a significant improvement in the network’s ability to accurately identify scene types. By exploiting these inter-scene interactions, HTMTL significantly enhances scene classification performance, making it a potent tool for advancing scene understanding and classification. Additionally, this study explores the contribution of individual tasks and task groupings on the performance of other tasks. To further validate the generality of HTMTL, we applied it to the Cityscapes dataset, where the results also show promise. This indicates the broad applicability and effectiveness of our approach across different datasets and scene types. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Accurate Identification of IoT Devices in the Presence of Wireless Channel Dynamics

Accurate Identification of IoT Devices in the Presence of Wi...

引用

Conference on Local computer Networks (LCN)

作者： Bhagyashri Tushir Vikram K Ramanna Yuhong Liu Behnam Dezfouli Department of Computer Science and Engineering Internet of Things Research Lab Santa Clara University USA

ISBN: (数字)9798350388008

ISBN: (纸本)9798350388015

Identifying IoT devices is crucial for network monitoring, security enforcement, and inventory tracking. However, most existing identification methods rely on deep packet inspection, which raises privacy concerns and adds computational complexity. Moreover, existing works overlook the impact of wireless channel dynamics on the accuracy of layer-2 features, thereby limiting their effectiveness in real-world scenarios. In this work, we define and use the latency of specific probe-response packet exchanges, referred to as "device latency," as the main feature for device identification. Additionally, we reveal the critical impact of wireless channel dynamics on the accuracy of device identification based on device latency features. Specifically, this work introduces "accumulation score" as a novel approach to capturing fine-grained channel dynamics and their impact on device latency when training machine learning models. We implement the proposed methods and measure the accuracy and overhead of device identification in real-world scenarios. The results confirm that by incorporating the accumulation score for balanced data collection and training machine learning algorithms, we achieve an F1 score of over 97% for device identification, even amidst wireless channel dynamics, a significant improvement over the 75% F1 score achieved by disregarding the impact of channel dynamics on data collection and device latency.

关键词： Wireless communication Training Privacy Accuracy Heuristic algorithms Data collection Inspection

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contexts

arXiv

引用

arXiv 2024年

作者： Tushir, Bhagyashri Ramanna, Vikram K. Liu, Yuhong Dezfouli, Behnam Internet of Things Research Lab Department of Computer Science and Engineering Santa Clara University United States

Identifying IoT devices is crucial for network monitoring, security enforcement, and inventory tracking. However, most existing identification methods rely on deep packet inspection, which raises privacy concerns and adds computational complexity. More importantly, existing works overlook the impact of wireless channel dynamics on the accuracy of layer-2 features, thereby limiting their effectiveness in real-world scenarios. In this work, we define and use the latency of specific probe-response packet exchanges, referred to as"device latency," as the main feature for device identification. Additionally, we reveal the critical impact of wireless channel dynamics on the accuracy of device identification based on device latency. Specifically, this work introduces"accumulation score" as a novel approach to capturing fine-grained channel dynamics and their impact on device latency when training machine learning models. We implement the proposed methods and measure the accuracy and overhead of device identification in real-world scenarios. The results confirm that by incorporating the accumulation score for balanced data collection and training machine learning algorithms, we achieve an F1 score of over 97% for device identification, even amidst wireless channel dynamics, a significant improvement over the 75% F1 score achieved by disregarding the impact of channel dynamics on data collection and device latency. Copyright © 2024, The Authors. All rights reserved.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Understanding and Enhancing Linux Kernel-based Packet Switching on WiFi Access Points

arXiv

引用

arXiv 2024年

作者： Zhang, Shiqi Gupta, Mridul Dezfouli, Behnam Internet of Things Research Lab Department of Computer Science and Engineering Santa Clara University United States

As the number of WiFi devices and their traffic demands continue to rise, the need for a scalable and high-performance wireless infrastructure becomes increasingly essential. Central to this infrastructure are WiFi Access Points (APs), which facilitate packet switching between Ethernet and WiFi interfaces. Despite APs’ reliance on the Linux kernel’s data plane for packet switching, the detailed operations and complexities of switching packets between Ethernet and WiFi interfaces have not been investigated in existing works. This paper makes the following contributions towards filling this research gap. Through macro and micro-analysis of empirical experiments, our study reveals insights in two distinct categories. Firstly, while the kernel’s statistics offer valuable insights into system operations, we identify and discuss potential pitfalls that can severely affect system analysis. For instance, we reveal the implications of device drivers on the meaning and accuracy of the statistics related to packet-switching tasks and processor utilization. Secondly, we analyze the impact of the packet switching path and core configuration on performance and power consumption. Specifically, we identify the differences in Ethernet-to-WiFi and WiFi-to-Ethernet data paths regarding processing components, multi-core utilization, and energy efficiency. We show that the WiFi-to-Ethernet data path leverages better multi-core processing and exhibits lower power consumption. Copyright © 2024, The Authors. All rights reserved.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Global video object segmentation with spatial constraint module

引用

Computational Visual Media 2023年第2期9卷 385-400页

作者： Yadang Chen Duolin Wang Zhiguo Chen Zhi-Xin Yang Enhua Wu Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of MacaoMacao 999078China State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of SciencesBeijing 100190China Faculty of Science and Technology University of MacaoMacao 999078China

We present a lightweight and efficient semisupervised video object segmentation network based on the space-time memory *** some extent,our method solves the two difficulties encountered in traditional video object segmentation:one is that the single frame calculation time is too long,and the other is that the current frame’s segmentation should use more information from past *** algorithm uses a global context(GC)module to achieve highperformance,real-time *** GC module can effectively integrate multi-frame image information without increased memory and can process each frame in real ***,the prediction mask of the previous frame is helpful for the segmentation of the current frame,so we input it into a spatial constraint module(SCM),which constrains the areas of segments in the current *** SCM effectively alleviates mismatching of similar targets yet consumes few additional *** added a refinement module to the decoder to improve boundary *** model achieves state-of-the-art results on various datasets,scoring 80.1%on YouTube-VOS 2018 and a J&F score of 78.0%on DAVIS 2017,while taking 0.05 s per frame on the DAVIS 2016 validation dataset.

关键词： video object segmentation semantic segmentation global context(GC)module spatial constraint

来源：评论

学校读者我要写书评

暂无评论

Automated Brain Abnormality Segmentation using Modified JAYA algorithm based Fuzzy C-Means Clustering 1

Automated Brain Abnormality Segmentation using Modified JAYA...

引用

1st International Conference on Software, Systems and Information Technology, SSITCON 2024

作者： Jeenath Shafana, N. Priya Lakshmi, S. Vijayalakshmi Ramani, U. Ramaraj, Kottaimalai Thilagaraj, M. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India Cmr Institute of Technology Department of Computer Science and Engineering Bengaluru India K Ramakrishnan College of Engineering Department of Electrical and Electronics Engineering Tiruchirappalli India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Krishnankoil India Mvj College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350352931

The main risk factors in humans, irrespective of gender or location, are anomalies of the brain, such as tumors and strokes. In healthcare facilities, the degree of disability and underlying cause of brain lesions are typically evaluated by means of regular methods created by trained clinicians. During this procedure, signals and images of the brain are collected in a controlled setting. Selecting an appropriate separation method is essential to getting the desired results. The novel JAYA algorithm, which relies on meta-heuristics, aids in the reclustering of the FCM segmentation results in our suggested techniques, yielding more productive delineation results with clear borders with 86% of Dice Score. However, the exploitation and exploration techniques for searching become more flexible and help identify the optimal solution faster by adjusting the desired function with respect to the accommodating cluster location and population size. Regarding the processing speed, optimal exploitation, and exploratory abilities, the suggested strategy outperforms the other available metaheuristic optimization techniques. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Online Education in Educational Institutions through the Integration of internet of things (IoT) 8

Improving Online Education in Educational Institutions throu...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Ramaraj, Kottaimalai Mathews, Ann Lynsha Helena Pratheeba, Hp Ramani, U. Sujitha, K.L. Thilagaraj, M. Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India Cmr Institute of Technology Department of Computer Science and Engineering Bengaluru India K Ramakrishnan College of Engineering Department of Electrical and Electronics Engineering Trichy India Mvj College of Engineering Department of Computer Science and Engineering Bengaluru India Mvj College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350367904

A key facilitating infrastructure for building intelligent structures that enable efficient in-person and virtual learning environments is the internet of things (IoT). The shift to smart learning, that includes IoT and Artificial Intelligence (AI) into the educational system, is enticing since it directly affects the motivation of learners, enrolment, participation, and in-depth understanding. Teaching and learning, management, examination, and class monitoring are only a few of the numerous issues that afflict conventional education. Many ingenious approaches to many facets of our lives are being made possible by modern advancements in information and communication technology (ICT);nonetheless, these imaginative concepts aren't adequately incorporated into the framework of education. The COVID-19 pandemic scenario, in specific, has brought out the need for innovative, creative approaches in the field of teaching. The present research examines previous investigations in the field and discusses the following topics: (i) issues with the current educational system and potential fixes;(ii) the shift to smart learning;and (iii) scientific hurdles (such as technological and cultural barriers) in making the move to smart learning. In accordance with these outcomes, creative approaches to the issues with the conventional system-such as smart teaching, smart evaluation, smart school environment, and smart management-are presented. The business and academic community may now include IoT, AI, and ICT into smart learning owing to the aforementioned experimental research's novel developments. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Three-Tier Architecture Framework with Blockchain Integration to Improve the Security in Healthcare Applications 14

A Three-Tier Architecture Framework with Blockchain Integrat...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Sivashankari, T. Pallikonda Rajasekaran, M. Ramaraj, Kottaimalai Arunprasath, T. Reddy, Muthangi Kantha Thilagaraj, M. Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Tamilnadu Krishnankoil India Kalasalingam Academy of Research and Education Department of Biomedical Engineering Tamilnadu Krishnankoil India Sri Vishnu Engineering College Department of Computer Science and Engineering AndhraPradesh Bhimavaram India Mvj College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350344837

The utilization of online diagnosis as a prevalent data service in contemporary healthcare systems involves the real-time collection of physical data through internet of things (IoT) devices, such as body sensors and software. This data informs instantaneous decision-making in the diagnostic process. However, the sensitive nature of the collected user data and diagnosis results poses a significant risk of privacy breaches or hacking incidents, potentially leading to misinformation or even fatal outcomes. The involvement of third-party cloud services exacerbates concerns about data protection. Compounding these issues, resource-constrained IoT devices often lack standard security measures. It is imperative to consider parameters such as accuracy, adaptability, low computation time, and the implementation of appropriate anonymity procedures. Addressing these challenges requires the development of a robust algorithm that prioritizes secure access to health records, with a particular emphasis on blockchain technology. To mitigate these shortcomings and ensure the secure storage of patient health data, this study advocates for the creation of a resilient three-tier architecture leveraging blockchain technology. This approach aims to enhance security measures, maintain data accuracy, and facilitate efficient access to health records while safeguarding patient confidentiality. © 2024 IEEE.

关键词： internet of things

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：