检索结果-内蒙古大学图书馆

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Kansal, Vipashi Shnain, Ammar Hameed Pushkarna, Gaurav Manjunatha Dixit, Krishna Kant Rajkumar, K. Varada Graphic Era Deemed to be University Department of Computer Science & Engg Dehradun India College of Technical Engineering The Islamic University Department of Computers Techniques Engg Najaf Iraq Lovely Professional University Phagwara India New Horizon College of Engg Department of Mechanical Engg Bangalore India Gla University Department of Electrical Engg Mathura India Mlr Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India

ISBN: (纸本)9798331518981

A new kind of image categorisation technology, Convolutional Neural Networks (CNNs) have shown themselves capable of astounding accuracy across a range of uses. Problems arise, however, when dealing with real-time applications in settings where resources are limited due to their computational complexity and resource needs. An extensive investigation on how to make convolutional neural networks (CNNs) better at picture classification is detailed in this work. We explore several optimization techniques, including network pruning, quantization, and the deployment of lightweight architectures such as MobileNet and SqueezeNet. Additionally, we investigate the impact of advanced training strategies like transfer learning and data augmentation on model performance. We show, by means of comprehensive tests, that our suggested approaches considerably reduce the memory footprint and computational cost of CNNs while preserving or even enhancing classification accuracy. Our findings provide valuable insights for deploying efficient CNN models in practical scenarios, paving the way for more accessible and scalable image classification solutions. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Lightweight privacy-aware secure authentication scheme for cyber-physical systems in the edge intelligence era

Lightweight privacy-aware secure authentication scheme for c...

引用

作者： Bakkiam Deebak, Deebak AL-Turjman, Fadi School of Computer Science and Engineering Vellore Institute of Technology Vellore India Artificial Intelligence Engineering Department Research Center for AI and IoT Near East University Mersin 10 Turkey

Internet of Things (IoT) and cyber-physical systems demand proper real-time data processing and analysis to fulfill the essential characteristics of seamless computing services such as less processing time, dynamic network management, and location awareness. With the evolution of mobile edge computing, numerous security and privacy issues have been addressed including policy management, authentication, access control, and confidentiality. The technologies such as big-data, Internet of Things, and cloud have improved the development of modern healthcare systems to improve the quality of medical services. It is nowadays integrating the computing methods and communication technologies such as wireless sensor networks, radio frequency identification, smartphones, and location awareness to collect and analyze the physiological data of the patient. The e-Health entities such as medical device, client, and server rely on analytical models to carry out early diagnosis and remote monitoring. As it is based on e-Health applications, a real-time healthcare system is preferred to integrate with mobile cloud computing. Since the medical data are hugely exposed to vulnerabilities, a lightweight privacy-aware secure authentication (LPASA) scheme is presented. To achieve better secure efficiencies, this article is preferable to use lightweight cryptographic operations, namely, one-way hashing function and bitwise exclusive-OR. Moreover, the formal and informal security analysis shows that the proposed LPASA can withstand the possible active and passive attacks such as replay, man-in-the-middle, privileged-insider, online-guessing, and so forth. The experimental analysis demonstrates that the proposed LPASA scheme achieves a better quality of services in terms of packet delivery ratio, energy consumption per data delivery bit, and percentage of packets with low latency to adopt in resource-constrained environments. © 2021 John Wiley & Sons, Ltd.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Cryptanalysis of TRUTH: Fixing a Protocol to Make it 5G-Compliant

Cryptanalysis of TRUTH: Fixing a Protocol to Make it 5G-Comp...

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： Munilla, J. Burmester, M. Caballero-Gil, P. University of Málaga Dpt. of Telecommunication Engineering Málaga29071 Spain Florida State Unviersity Department of Computer Science TallahasseeFL32304 United States University of La Laguna Dept. of Computer Science and Ai Tenerife La Laguna Spain

ISBN: (纸本)9798350364910

Trust and security are critical deployment require-ments for Industrial Internet of Things (IIoT) networks. A recent protocol, called TRUTH, integrates security mechanisms for authentication and privacy alongside a Dempster-Shafer based trust model, to assess the trustworthiness of collected data. We analyze this protocol and show that it does not comply with the implementation requirements of the 5G standard, and that flaws in the identification of involved parties hinder its adoption by 5G devices. We show how to fix this protocol and tailor it for the specific 5G implementation constraints, by enhancing its computational and communication performance. Finally, we show how to prove the security of this fixed protocol (TRUTH +) using the Tamarin automated verification tool. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

DiffVoice: Text-to-Speech with Latent Diffusion 48

DiffVoice: Text-to-Speech with Latent Diffusion

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Liu, Zhijun Guo, Yiwei Yu, Kai Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute X-Lance Lab Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9781728163277

In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training, and then jointly model the duration and the latent representation with a diffusion model. Subjective evaluations on LJSpeech and LibriTTS datasets demonstrate that our method beats the best publicly available systems in naturalness. By adopting recent generative inverse problem solving algorithms for diffusion models, DiffVoice achieves the state-of-the-art performance in text-based speech editing, and zero-shot adaptation. © 2023 IEEE.

关键词： diffusion probabilistic model speech editing speech synthesis variational autoencoder zero-shot adaptation

来源：评论

学校读者我要写书评

暂无评论

Sensorimotor System Design of Socially Intelligent Robots 26th

Sensorimotor System Design of Socially Intelligent Robots

引用

26th International Conference on Pattern Recognition, ICPR 2022

作者： Trajcevski, Aleksander Filho, Helio Perroni Javed, Nizwa Naheyan, Tasneem Bhargava, Kartikeya Elder, James H. Department of Electrical Engineering and Computer Science Centre for AI & Society York University TorontoONM3J 1P3 Canada

We describe and demonstrate a sensorimotor architecture for social robots, highlighting in particular the value of attentive sensing for acquisition of more detailed information about people in the far field, and how ... 详细信息

ISBN: (纸本)9783031377440

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of Covariates Effects on Periocular Biometrics: A Robust Security Assessment Framework

引用

Journal of Data and Information Quality 2023年第2期15卷 1-25页

作者： Kumar, Gautam Bakshi, Sambit Sangaiah, Arun Kumar Sa, Pankaj Kumar National Institute of Technology Rourkela Sector II Odisha Rourkela769 008 India International Graduate Institute of Ai National Yunlin University of Science and Technology Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

The growing integration of technology into our lives has resulted in unprecedented amounts of data that are being exchanged among devices in an Internet of Things (IoT) environment. Authentication, identification, and device heterogeneities are major security and privacy concerns in IoT. One of the most effective solutions to avoid unauthorized access to sensitive information is biometrics. Deep learning-based biometric systems have been proven to outperform traditional image processing and machine learning techniques. However, the image quality covariates associated with blur, resolution, illumination, and noise predominantly affect recognition performance. Therefore, assessing the robustness of the developed solution is another important concern that still needs to be investigated. This article proposes a periocular region-based biometric system and explores the effect of image quality covariates (artifacts) on the performance of periocular recognition. To simulate the real-time scenarios and understand the consequences of blur, resolution, and bit-depth of images on the recognition accuracy of periocular biometrics, we modeled out-of-focus blur, camera shake blur, low-resolution, and low bit-depth image acquisition using Gaussian function, linear motion, interpolation, and bit plan slicing, respectively. All the images of the UBIRIS.v1 database are degraded by varying strength of image quality covariates to obtain degraded versions of the database. Afterward, deep models are trained with each degraded version of the database. The performance of the model is evaluated by measuring statistical parameters calculated from a confusion matrix. Experimental results show that among all types of covariates, camera shake blur has less effect on the recognition performance, while out-of-focus blur significantly impacts it. Irrespective of image quality, the convolutional neural network produces excellent results, which proves the robustness of the developed model. © 2023 Co

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Automatic Face Recognition Using Legendre Moments and Auto-Associative Memory

Automatic Face Recognition Using Legendre Moments and Auto-A...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Jay Kant Pratap Singh Yadav Zainual Abdin Jaffery Laxman Singh Electrical Engineering Department Jamia Millia Islamia Central University New Delhi India Computer Science & Engg. (AI&ML) Department Krishna Group of Institutions Ghaziabad India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

Face recognition involves identifying or verifying a person based on their facial features. This study introduces a method using Legendre moments for feature extraction combined with an auto-associative memory approach, specifically a “Multi-connection Hopfield Neural Network” to enhance accuracy and robustness. The method uses a single image per person, optimizing both the computation time and memory usage. Tested on the ORL (Olivetti Research Laboratories) dataset, the approach achieved a 99.0% recognition rate, outperforming other state-of-the-art methods. Additionally, the system demonstrated resilience to noise, maintaining a 95.75 % rate with 50 % random noise.

关键词： Training Associative memory Accuracy Face recognition Noise Hopfield neural networks Feature extraction Robustness Noise measurement Resilience

来源：评论

学校读者我要写书评

暂无评论

Mern (Mongodb, Express-Js, React-Js, Node-Js) Stack Web-Based Streaming and Broadcasting Application

Mern (Mongodb, Express-Js, React-Js, Node-Js) Stack Web-Base...

引用

Electrical Electronics and Computing Technologies (ICEECT), International Conference on

作者： Vineet Kumar Singh Priyank Awasthi Lakshman Tripathi Sahil Thakur Priyanka Singh Department Of Computer Science & Engineering (AI) ABES Institute of Technology Ghaziabad India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

In this paper, authors present a comprehensive approach to develop a web-based streaming and broadcasting application, centering on the integration of WebRTC (Web Real-Time Communication) and RTMP (Real-Time Messaging Protocol) technologies. Using the advantages of both traditions while addressing their unique limitations, the system aims to provide a consistent level of client *** engineering comprises of a WebRTC server for real-time communication between peers, encouraging the capture and transmission of audio and video streams. In order to increase compatibility and flexibility, WebRTC streams are converted to RTMP format using the Simple RTMP Server (SRS). More widespread availability across platforms and devices that facilitate RTMP-based playback is enabled by this *** integration of WebRTC and RTMP advancements within the streaming application, users can benefit from instantaneous communication features while ensuring compatibility with a wider variety of playback devices. This method provides an adaptable setup suitable for many streaming and broadcasting situations, including live events, video conferences, and online multimedia content delivery.

关键词： Digital multimedia broadcasting computers Protocols Streaming media Peer-to-peer computing Multimedia communication Servers Streams WebRTC Videoconferences

来源：评论

学校读者我要写书评

暂无评论

Real-time Twist Rebar Detection System exploiting GAN-based Data Augmentation technique 1

Real-time Twist Rebar Detection System exploiting GAN-based ...

引用

1st International Workshop on Intelligent Software engineering, ISE 2022

作者： Park, Jong Chan Kim, Gun-Woo Department of AI Convergence Engineering Gyeongsang National University Jinju Korea Republic of School of Computer Science Department of AI Convergence Engineering Gyeongsang National University Jinju Korea Republic of

Currently, ai image analysis research is being conducted on automated cutting, bending, and loading systems, which are the main facilities of rebar processing factories. For automation, various datasets through machine vision cameras are required. However, environmental factors include difficult data collection or high production costs to collect datasets in the production process. To solve these problems, we propose a real-time twist rebar detection system based on GAN (Generative adversarial network), with real rebar datasets collected from 20 rebar videos. In this paper, we generated additional datasets from a deep image generation network and detected rebars' endpoints through YOLO (You Only Look Once) v4, a deep-learning object detection model. In experiments, we generated rebar images corresponding to normal and abnormal, the measured quality between real rebar dataset and generated synthetic rebar dataset by FID (Frechet Inception Distance). As a result, FID measurements showed the normal synthetic rebar dataset 79.363 and the abnormal synthetic rebar dataset 113.973. After that, as a result of training in YOLO v4 by combining the synthetic rebar dataset generated from GAN and the real rebar dataset, we obtained the mean Average Precision (mAP) of 100% and a misdetection rate of 5% compared to the real rebar dataset, the mAP increased by 0.6%, and decreased by 10%. Overall, our results demonstrate a strong effect on rebar twist detection accuracy and misdetection rate. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hypothesis testing the circuit hypothesis in LLMs 24

Hypothesis testing the circuit hypothesis in LLMs

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Claudia Shi Nicolas Beltran-Velez Achille Nazaret Carolina Zheng Adrià Garriga-Alonso Andrew Jesson Maggie Makar David M. Blei Department of Computer Science Columbia University New York FAR AI Computer Science and Engineering University of Michigan Ann Arbor

ISBN: (纸本)9798331314385

Large language models (LLMs) demonstrate surprising capabilities, but we do not understand how they are implemented. One hypothesis suggests that these capabilities are primarily executed by small subnetworks within the LLM, known as circuits. But how can we evaluate this hypothesis? In this paper, we formalize a set of criteria that a circuit is hypothesized to meet and develop a suite of hypothesis tests to evaluate how well circuits satisfy them. The criteria focus on the extent to which the LLM's behavior is preserved, the degree of localization of this behavior, and whether the circuit is minimal. We apply these tests to six circuits described in the research literature. We find that synthetic circuits - circuits that are hard-coded in the model - align with the idealized properties. Circuits discovered in Transformer models satisfy the criteria to varying degrees. To facilitate future empirical studies of circuits, we created the circuitry package, a wrapper around the TransformerLens library, which abstracts away lower-level manipulations of hooks and activations. The software is available at https://***/blei-lab/circuitry.

关键词：

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：