检索结果-内蒙古大学图书馆

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Archana, M. Joseph, Ashwin Antony Ajith, Alex V. Koshy, Alan N. Saritha, S. Department of Computer Science Engineering Rajagiri School of Engineering and Technology Kochi India

ISBN: (纸本)9789819765805

Advent of GAN networks has enabled several tasks such as text to face generation easier. It helps in synthesizing several instances of data from the actual data. It gives an idea on new possibilities for existing dataset. The current scenario in literature sees a parade of GAN architectures. The performance of each GAN architecture varies in a wide range of outputs. Hence, there always exists a confusion of the GAN architecture to be chosen for the purpose of the task in question. This paper attempts to make a comparative evaluation of two famous GAN architectures, namely, StyleGAN and DCGAN. The architectures are implemented and the images generated are compared on the basis of the quality of images. It is seen that StyleGAN responds more accurately to features like smile, age, and gender. From the experiments, it is seen that the FID score of StyleGAN has a lower value as compared to that of DCGAN. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Suitability of SDN and MEC to facilitate digital twin communication over LTE-A

引用

Digital Communications and Networks 2024年第2期10卷 347-354页

作者： Hikmat Adhami Mohammad Alja’afreh Mohamed Hoda Jiaqi Zhao Yong Zhou Abdulmotaleb El Saddik Mohamed bin Zayed University of Artificial Intelligence Masdar CityAbu DhabiUnited Arab Emirates School of Computer Science and Technology China University of Mining and TechnologyXuzhou221116China School of Electrical Engineering and Computer Science University of OttawaOttawaONK1N 6N5Canada

Haptic is the modality that complements traditional multimedia,i.e.,audiovisual,to evolve the next wave of innovation at which the Internet data stream can be exchanged to enable remote skills and control *** will require ultra-low latency and ultra-high reliability to evolve the mobile experience into the era of Digital Twin and Tactile *** the 5th generation of mobile networks is not yet widely deployed,Long-Term Evolution(LTE-A)latency remains much higher than the 1 ms requirement for the Tactile Internet and therefore the Digital *** work investigates an interesting solution based on the incorporation of Software-defined networking(SDN)and Multi-access Mobile Edge Computing(MEC)technologies in an LTE-A network,to deliver future multimedia applications over the Tactile Internet while overcoming the QoS *** network scenarios were designed and simulated using Riverbed modeler and the performance was evaluated using several time-related Key Performance Indicators(KPIs)such as throughput,End-2-End(E2E)delay,and *** best scenario possible is clearly the one integrating MEC and SDN approaches,where the overall delay,jitter,and throughput for haptics-attained 2 ms,0.01 ms,and 1000 packets per *** results obtained give clear evidence that the integration of,both SDN and MEC,in LTE-A indicates performance improvement,and fulfills the standard requirements in terms of the above KPIs,for realizing a Digital Twin/Tactile Internet-based system.

关键词： LTE-A 5G Digital twin Tactile Internet KPIs SDN MEC NFV Haptic

来源：评论

学校读者我要写书评

暂无评论

Fault-tolerant capability analysis of six-phase induction motor with distributed, concentrated, and pseudo-concentrated windings

引用

Scientia Iranica 2024年第10期31卷 775-789页

作者： Alemi-Rostami, Mehdi Rezazadeh, Ghasem Tahami, Farzad Akbari-Resketi, Hamid Reza Ministry of Science Research and Technology Tehran Iran School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Department of Electrical Engineering Sharif University of Technology Tehran Iran Department of Electrical and Computer Engineering Babol Noshirvani University of Technology Babol Iran

Six-phase motors are becoming more popular because of their advantages such as lower torque ripple, better power distribution per phase, higher efficiency, and fault-tolerant capability compared to the three-phase ones. This paper presents the fault-tolerant capability analysis of a symmetrical six-phase induction motor equipped with distributed, conventional concentrated, and pseudo-concentrated windings under open-circuit fault scenarios. For further investigation, different load types such as constant-speed, constant-torque, and constant-power are applied to the motor. Two concepts of magnetic and physical phase separations are introduced as factors affecting the motor reliability. Analytically, these factors give an insight into how the pseudo-concentrated winding could be a fault-tolerant alternative. Moreover, five parameters such as the change of output power, power loss, power factor, efficiency, and expected load loss are considered as the fault-tolerant capability parameters to evaluate the windings reliability. The aforementioned parameters are reported using the finite element analysis for different fault scenarios and different load types. Although the baseline motor dimensions are not optimized for applying the pseudo-concentrated winding, the pseudo-concentrated shows a promising performance with high fault-tolerant capability. © 2024 Sharif University of technology. All rights reserved.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

A video data hiding technique based on pixel sequence, weight interpolation and quorum function

引用

Multimedia Tools and Applications 2024年第41期83卷 88881-88901页

作者： Roselinkiruba, R. Jothi, C. Saranya Koushik, C.P. Keerthika, A. Sathya, Vanlin School of Computer and Science Engineering Vel Tech Rangarajan Dr.Sagunthala R & D Institute of Science and Technology Chennai Avadi India School of Computer and Science Engineering VIT Bhopal University Bhopal India Electronics and Communication Engineering Aarupadai Veedu Institute of Technology Chennai India Celona Inc CampbellCA United States

The development of multimedia technology has increased the challenge in protecting the information. This paper proposes an effective method for data hiding in videos based on the Pixel Sequence (PS), weight interpolation to protect the secret data from intruders. Initially, the noise is removed from the video with the help of median filter and Moving Objects (MO) inside the frames having different backgrounds are accurately detected using Fast Region-based Convolution Neural Network (FR-CNN). Next, the MO and Non Moving Object (NMO) pixel from each frame are mapped with the adjacent frames to determine the weights applying PS. Then, the cover video is up-scaled with interpolated pixels based on weights of MO and NMO. Finally, the secret data are hidden inside the both interpolated and non-interpolated pixels elevate Embedding Capacity (EC). In interpolated pixels, both Most Significant Bit (MSB) and Least Significant Bit (LSB) of each frames based on their weight are utilized to hide data. Whereas, in non-interpolated pixels, Quorum Function (QF) is used to embed data. Two different data embedding techniques are adopted in each frame to enhance the security. The performance evaluation of the proposed method out-performs the existing methods in terms of precision and recall. Experimental results also show that the stego-video quality is uncompromised and is resistive to security attacks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Hardware-friendly rate estimation algorithm and architecture design for AVS3

引用

Multimedia Tools and Applications 2025年 1-19页

作者： Yan, Yunyao Xiang, Guoqing Chen, Jie Huang, Xiaofeng Zhang, Peng Jia, Huizhu Xie, Xiaodong School of Electronic and Computer Engineering Peking University Shenzhen China School of Computer Science Peking University Beijing China Advanced Institute of Information Technology Peking University Hangzhou China School of Communication Engineering Hangzhou Dianzi University Hangzhou China

To enhance the capabilities of advanced video coding for emerging applications, the AVS3 standard has been introduced to double the coding efficiency compared to its predecessor, the AVS2 standard. It incorporates sophisticated coding tools, such as advanced rate-distortion optimization (RDO), to select the optimal coding mode. The AVS3 standard further refines bit rate compression through Advanced Entropy Coding (AEC) within the RDO process. However, AEC demands significant computational resources due to its high data dependency and involves complex steps like binarization, context modeling, interval subdivision, renormalization, handling of outstanding bits, and context updating. Notably, the time complexity of AEC is predominantly due to context updating and interval subdivision, which are recursive and thus pose challenges for real-time applications, particularly in hardware implementations. Addressing these challenges, this paper introduces an adaptive rate estimation algorithm using a hardware-friendly piece-wise linear function to expedite bit rate calculations for AVS3 applications. Initially, we develop a linear rate estimation method based on the statistics of bin numbers. To preserve high coding performance, we further propose an adaptive model parameter updating method that adjusts weights dynamically based on varying video content. Building on this fast rate estimation algorithm, we propose a high-throughput hardware architecture that incorporates pipelining and parallelization to meet the stringent real-time requirements for 4K@120fps ultra-high-definition video at 200 MHz, with only a minimal increase in BD-rate by 1.06% under the All-Intra (AI) configuration. To our knowledge, this is the pioneering study focusing on hardware-oriented rate estimation for the AVS3 standard, marking a significant advancement in the field of video coding technology. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Face Generation and Recognition in Forensic science 11

Face Generation and Recognition in Forensic Science

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Ravi, Gayathri Joy, Heynes Jitto, Jeffin Joshy, Jocelyn Jose, Jisha Mary Rajagiri School of Engineering & Technology Dept. of Computer Science and Engineering India

ISBN: (纸本)9798350379136

Suspect identification can be challenging for forensic investigations since standard procedures are time-consuming and prone to mistakes. This calls for the creation of novel approaches utilizing developments in machine learning (ML) and artificial intelligence (AI). In order to overcome these obstacles, the proposed Face Generation and Recognition in Forensic science will make use of sophisticated recognition algorithms and AI-based face generation models. Fully trained Stable Diffusion model is applied to generate high-quality face images from textual descriptions. Image Generation, Text Guided Image Manipulation using Denoising Diffusion Probabilistic Models (DDPMs), and Dataset Matching are the three primary components of the process. Using a stable diffusion model, Image Generation quickly creates high-resolution images from word prompts by combining an autoencoder (VAE), U-Net, and text encoder. With the introduction of an alternate noise space for DDPMs, Text Guided picture Manipulation makes it possible to do meaningful picture altering tasks in response to text prompts. VGG-16 , a convolutional neural network architecture is used in dataset matching to extract features and calculate similarity, which makes dataset alignment and comparison easier. The suggested methodology gives law enforcement authorities effective tools for identifying suspects, which represents a substantial development in forensic investigations. The project intends to increase the efficiency of criminal investigations, accelerate the matching process with large datasets, and enhance the accuracy of facial sketches by utilizing AI and ML approaches. The approach's ability to produce coherent and contextually relevant face images is validated by experimental results, which also show the approach's potential for speeding up the conclusion of criminal cases, particularly unsolved cold cases. All things considered, Face Generation and Recognition in Forensic science is a promising step in st

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Summarization for PDF Documents using Large Language Models 4

Context-Aware Summarization for PDF Documents using Large La...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Ramprasad, Akshara Sivakumar, P. School of Computer Science and Engineering Vellore Institute of Technology B. Tech Computer Science with specialization in AI & ML Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350385793

In an era characterized by the overflow of textual information, the demand for effective text summarization techniques has become increasingly evident. This research study presents a novel solution to address this demand: the development of a PDF Summarizer Generative AI Platform for context-aware text and document summarization. The developed platform empowers users to generate informative summaries from lengthy textual documents. It features an interface powered by Gradio for enabling user-friendly accessibility. Equipped with essential components such as OpenAI's language models for text comprehension, Chroma vector enables document embedding and conversational retrieval chains for contextual understanding, where the platform offers a comprehensive solution. Users can effortlessly upload documents in various formats, including PDFs, and interactively engage with the system to obtain concise summaries tailored to their specific requirements. © 2024 IEEE.

关键词： Chroma Database (ChromaDB) Gradio LangChain Large Language Models (LLM) OpenAI

来源：评论

学校读者我要写书评

暂无评论

OptiFog: A Framework for Acquiring State Information and Predicting Resource Availability for Task Offloading in Cooperative Fog-Networks

引用

IEEE Transactions on Services Computing 2024年 1-13页

作者： Alam, Mehbub Ahmed, Nurzaman Ghosh, Shyamal Matam, Rakesh Barbhuiya, Ferdous Ahmed Department of Computer Science and Engineering Indian Institute of Information Technology Guwahati India Department of Computer Science Dartmouth College Hanover USA School of Data Science Indian Institute of Science Education and Research Thiruvananthapuram India

The primary objective of fog computing is to minimize the reliance of IoT devices on the cloud by leveraging the resources of fog network. Typically, IoT devices offload computation tasks to fog to meet different task requirements such as latency in task execution, computation costs, etc. So, selecting such a fog node that meets task requirements is a crucial challenge. To choose an optimal fog node, access to each node's resource availability information is essential. Existing approaches often assume state availability or depend on a subset of state information to design mechanisms tailored to different task requirements. In this paper, OptiFog: a cluster-based fog computing architecture for acquiring the state information followed by optimal fog node selection and task offloading mechanism is proposed. Additionally, a continuous time Markov chain based stochastic model for predicting the resource availability on fog nodes is proposed. This model prevents the need to frequently synchronize the resource availability status of fog nodes, and allows to maintain an updated state information. Extensive simulation results show that OptiFog lowers task execution latency considerably, and schedules almost all the tasks at the fog layer compared to the existing state-of-the-art. IEEE

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

DUE-MVSNet: Learning Multi-view Stereo Based on Dual Uncertainty Estimation 41st

DUE-MVSNet: Learning Multi-view Stereo Based on Dual Uncert...

引用

41st computer Graphics International Conference, CGI 2024

作者： Cao, Mingwei Nian, Siqi Yi, Jun School of Computer Science and Technology Anhui University Hefei230601 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

ISBN: (纸本)9783031820205

Many multi-view stereo networks employing a cascade structure can efficiently estimate depth while conserving memory. However, the accuracy of the depth map in the fine stage heavily relies on the depth map estimated in the coarse stage. Additionally, the multi-stage depth maps generated by the cascaded structure are simply used to calculate losses without further utilization, which results in the loss of inter-stage differentiation information. To address these issues, we propose a method called DUE-MVSNet. We use dual uncertainty estimation to mitigate the adverse effects introduced by the cascade structure. Specifically, we design an adjacent stage uncertainty (ASU) module and a pair-wise stage uncertainty (PSU) module. The ASU module dynamically adjusts the depth hypothesis range for the current stage by learning the uncertainty of the previous stage. The PSU module estimates the uncertainty between each pair of stages, mitigating the adverse effects of high uncertainty regions. We evaluated our method on the DTU and Tanks & Temples datasets. Experimental results show that our method achieves superior reconstruction results compared to the state-of-the-art methods. Code is available at https://***/caomw/due-mvsnet. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Event Management System Using Spatial and Event Attribute Information

引用

SN computer science 2025年第3期6卷 1-9页

作者： Setia, Sonia Anjli, Km Bisht, Upasana Jyoti Raj, Dharm Department of Computer Science & Engineering Sharda School of Engineering & Technology Sharda University Uttar Pradesh Greater Noida India Department of Computer Science Institute of Innovation in Technology & Management Delhi Janakpuri India Department of Computer Science and Engineering ITS Engineering College Greater Noida India

The event management mechanism matches messages that have been subscribed to and events that have been published. To identify the subscriptions that correspond to the occurrence inside the category, it must first run a clustering operation on the subscription message data and determine the category to which the event belongs. In this work, we offer an on-the-fly publish-subscribe technique that can handle on-the-fly subscription changes and category modifications in a distributed environment, as well as the synchronization of spatial information and event attribute information. Additionally, without any prior information, clustering and matching processes can be carried out rapidly. The publish-subscribe method is implemented on a distributed system, and a load-balancing solution is proposed for the algorithm on the distributed system. We then constructed our cluster and used real data to empirically evaluate the suggested publish-subscribe technique. Experiments show that incorporating both similarity and relevance with frequency, compared to focusing on similarity alone, significantly decreases the number of categories which need to be matched for events. This leads to a 15.5% improvement in the speed of matching events and subscriptions. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Clustering algorithms Distributed systems Publish-and-subscribe systems

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：