检索结果-内蒙古大学图书馆

International Symposium on parallel and distributed processing with Applications, ISPA

作者： Junhao Xu Dongbiao He Chen Zhang Xu Zhou Zhongxing Ming Laizhong Cui College of Computer Science and Software Engineering Shenzhen University Sangfor Technologies Inc Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

The rapid advancement of generative artificial intelligence (GAI) has led to the creation of transformative applications such as ChatGPT, which significantly boosts text processing efficiency and diversifies audio, image, and video content. Beyond digital content creation, GAI’s capability to analyze complex data distributions holds immense potential for next-generation networks and communications, especially given the swift rise of video conferencing applications (VCAs). This paper presents a dynamic, real-time method for detecting anomalous network links in video conferencing applications. The proposed tool, MonkeyGPT, generates tracing representations of network activity and trains a large language model from scratch to serve as a detection system based on network traffic data. Unlike traditional methods, MonkeyGPT provides an unrestricted search space and does not rely on predefined rules or patterns, enabling it to detect a wider range of anomalies. We demonstrate the effectiveness of MonkeyGPT as an anomaly detection tool in real-world VCAs. The results indicate that the model possesses strong detection capabilities, achieving an accuracy rate of over 97%. It is applicable to various platforms, including Zoom, Microsoft Teams, Tencent Meeting, and Feishu, showcasing its robust adaptability.

关键词： Accuracy Generative AI Large language models Telecommunication traffic Streaming media Real-time systems Data models Anomaly detection Videoconferences Text processing

来源：评论

学校读者我要写书评

暂无评论

Human Tissue Cell image Segmentation optimization Algorithm Based on Improved U-net Network 6

Human Tissue Cell Image Segmentation optimization Algorithm ...

引用

6th International conference on Information and Computer Technologies, ICICT 2023

作者： Ying, Jie Jing, Xin Qin, Chenyang Huang, Wei University of Shanghai for Science and Technology School of Optical Electrical and Computer Engineering Shanghai200093 China

ISBN: (纸本)9798350300956

In medical testing and diagnosis, cells as the basic structure of human body, have received extensive attention in pathological research. The detection and segmentation of cells or nuclei play an important role in describing molecular morphological information. The accuracy of human tissue cells segmentation still needs to be improved, and the network segmentation results have boundary blurring and noise pixels interference. In this paper, an improved U-net network model is proposed. Aiming at the problem of simple stacking of the same convolution operation, a parallel structure for multi-scale image feature extraction is designed. Through the setting of multiple convolution operations and combining different feature fusion methods, a better convolution block structure is obtained. The network segmentation image is optimized through the secondary segmentation of Otsu method and morphological processing, and the final segmentation result is obtained. Finally, the cell contour and centroid are displayed on the original image, and the nuclear center was calculated by image moment. The experiments were carried out on the human organ H&E cell data set. The experimental results show that the Dice coefficient, Jaccard similarity coefficient, recall and accuracy of the improved U-net network model for H&E cell image segmentation reach 0.8260, 0.60, 0.8380 and 0.8270 respectively. Compared with U-net network, the above parameters of the improved U-net model are increased by 1.7%, 3.9%, 1.2% and 2.2% respectively. Compared with CNN network, the accuracy rate is improved by 3.5%, and cell segmentation is more accurate than other literatures. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

3DVSR: 3D EPI volume-based approach for angular and spatial light field image super-resolution

引用

SIGNAL processing 2022年 192卷 108373-108373页

作者： Trung-Hieu Tran Berberich, Jan Simon, Sven Univ Stuttgart Inst Parallel & Distributed Syst D-70569 Stuttgart Germany

Light field (LF) imaging, which captures both spatial and angular information of a scene, is undoubtedly beneficial to numerous applications. Although various techniques have been proposed for LF acquisition, achieving both angularly and spatially high-resolution LF remains a technology challenge. In this paper, a learning-based approach applied to 3D epipolar image (EPI) is proposed to reconstruct high-resolution LF. Through a 2-stage super-resolution framework, the proposed approach effectively addresses various LF super-resolution (SR) problems, i.e., spatial SR, angular SR, and angular-spatial SR. While the first stage provides flexible options to up-sample EPI volume to the desired resolution, the second stage, which consists of a novel EPI volume-based refinement network (EVRN), substantially enhances the quality of the high-resolution EPI volume. An extensive evaluation on 90 challenging synthetic and real-world light field scenes from 7 published datasets shows that the proposed approach outperforms state-of-the-art methods to a large extend for both spatial and angular super-resolution problem, i.e., an average peak signal to noise ratio improvement of more than 2.0 dB, 1.4 dB, and 3.14 dB in spatial SR x2, spatial SR x4, and angular SR respectively. The reconstructed 4D light field demonstrates a balanced performance distribution across all perspective images and presents superior visual quality compared to the previous works. (C) 2021 Elsevier B.V. All rights reserved.

关键词： 3D-EPI volume Angular super-resolution Deep learning Light field Spatial super-resolution

来源：评论

学校读者我要写书评

暂无评论

parallel Coregistration Algorithm For Sar images Based On Hadoop

Parallel Coregistration Algorithm For Sar Images Based On Ha...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jiawei Li Guobing Zeng Huaping Xu School of Electronic and Information Engineering Beihang University Beijing China

As the availability of SAR images continues to grow, efficient coregistration of massive SAR images presents a greater challenge. Traditional serial coregistration methods impose an unbearable time overhead. To reduce this overhead and make full use of computing resources, a parallel coregistration strategy based on Hadoop is proposed for SAR images. The Hadoop distributed File System (HDFS) is used to store SAR image data in chunks, and Hadoop's distributed computing strategy MapReduce is used to realize distributed parallel processing of SAR images. Two distributed parallel coregistration methods are presented with the proposed parallel strategy: one based on the maximum correlation method and the other on the DEM-assisted coregistration method. These methods are evaluated through coregistration experiments on the same dataset, and they are verified by comparing the coregistration results and processing time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel O(log(n) ) Computation of the Adjacency of Connected Components 3rd

Parallel O(log(n) ) Computation of the Adjacency of Conne...

引用

3rd International conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2022

作者： Banaeyan, Majid Kropatsch, Walter G. TU Wien Pattern Recognition and Image Processing Group 193/03 Vienna Austria

ISBN: (纸本)9783031092817

Connected Component Labeling (CCL) is a fundamental task in pattern recognition and image processing algorithms. It groups the pixels into regions, such that adjacent pixels have the same label while pixels belonging to distinct regions have different labels. The common linear-time raster scan CCL techniques have a complexity of O(image- size) in a 2D binary image. To speed up the procedure of the CCL, the paper proposes a new irregular graph pyramid. To construct this pyramid, we use a new formalism [1] that introduces an order of the pixels in the base grid to detect the redundant edges through the hierarchical structure. These redundant edges, unlike the usual methods of constructing the irregular pyramid, are removed before contracting the edges. This not only simplifies the construction processes but may decrease memory consumption by approximately half. To perform the CCL task efficiently the proposed parallel algorithm reduces the complexity to O(log(n) ) where the n is the diameter of the largest connected component in the image. In addition, using an efficient combinatorial structure the topological properties of the connected components including adjacency of CCs, multi-boundaries and inclusions are preserved. Finally, the mathematical proofs provide fully parallel implementations and lead to efficient results in comparison with the state-of-the-art. © 2022, Springer Nature Switzerland AG.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Pixel Adapter: A Graph-Based Post-processing Approach for Scene Text image Super-Resolution 23

Pixel Adapter: A Graph-Based Post-Processing Approach for Sc...

引用

31st ACM International conference on Multimedia (MM)

作者： Zhang, Wenyu Deng, Xin Jia, Baojun Yu, Xingtong Chen, Yifan Ma, Jin Ding, Qing Zhang, Xinming Univ Sci & Technol China Hefei Peoples R China China Merchants Bank Chengdu Peoples R China

ISBN: (纸本)9798400701085

Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is crucial in the process of converting low-resolution images to high-resolution ones, has received little attention in existing works. To address this issue, we propose the Pixel Adapter Module (PAM) based on graph attention to address pixel distortion caused by upsampling. The PAM effectively captures local structural information by allowing each pixel to interact with its neighbors and update features. Unlike previous graph attention mechanisms, our approach achieves 2-3 orders of magnitude improvement in efficiency and memory utilization by eliminating the dependency on sparse adjacency matrices and introducing a sliding window approach for efficient parallel computation. Additionally, we introduce the MLP-based Sequential Residual Block (MSRB) for robust feature extraction from text images, and a Local Contour Awareness loss (L-lca) to enhance the model's perception of details. Comprehensive experiments on TextZoom demonstrate that our proposed method generates high-quality super-resolution images, surpassing existing methods in recognition accuracy. For single-stage and multi-stage strategies, we achieved improvements of 0.7% and 2.6%, respectively, increasing the performance from 52.6% and 53.7% to 53.3% and 56.3%. The code is available at https://***/wenyu1009/RTSRN.

关键词： scene text image super-resolution vision backbone pixel-wise graph attention

来源：评论

学校读者我要写书评

暂无评论

Simulation of distributed information networks load balancing and resource management 2

Simulation of distributed information networks load balancin...

引用

2nd International conference on Conflict Management in Global Information Networks, CMiGiN 2022

作者： Shestak, Yanina Myrutenko, Larysa Toliupa, Serhii Onyigwang, Ogbu James Solodovnyk, Valeriia Jinjikhadze, Melkisadeg Yaremko, Halyna Taras Shevchenko National University of Kyiv Bohdana Havrylyshyna 24 Kyiv02000 Ukraine Akaki Tsereteli State University Kutaisi Georgia Lviv Polytechnic National University S. Bandery Street 12 Lviv79013 Ukraine

Current approaches in parallel processing of requests used in modern distributed information systems are considered. The multilevel scheme of balancing the resources of the infrastructure of the distributed information system based on the graph of tasks is constructed. methods for estimating the optimization of the graph of problems based on the indicators of the length of the normalized graph and the normalized energy distribution are determined. Mathematical modeling is performed for calculation methods by hierarchical structure, algorithms for graph partitioning, methods based on algebraic graph theory, and structuring of the type "Diamond Dags" with uniform, binomial, and geometric distributions. A comparison of the results of mathematical modeling with statistical data showed the level of adequacy of the developed mathematical model. © 2022 Copyright for this paper by its authors.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Efficient Gender Recognition with Deep Learning Models on Balanced Facial image Datasets 8

Efficient Gender Recognition with Deep Learning Models on Ba...

引用

8th International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Poddar, Kishan Sharma, Bhanu Chitkara University Chitkara University Institute of Engineering & Technology Punjab India

ISBN: (纸本)9798350376425

From security to marketing to human-computer interaction, gender recognition from facial photographs is a basic task in many disciplines. This effort intends to develop an appropriate gender recognition model using a balanced dataset including 1,292 images equally distributed between men and women. Training, validation and testing sets were created from diverse age groups, ethnicities and environments of the dataset to ensure proper evaluation. Transfer learning methods were used to accelerate training and increase generalization using ResNet50, a deep learning model developed on convolutional neural networks (CNN). Designed for the specific difficulty of gender recognition, the pre-trained model was developed on leveraging characteristics obtained from a large dataset to achieve amazing accuracy with minimal data and processing resources. Both suitable for classification issues, the model was optimized using cross-entropy loss and Adam optimizer. Performance evaluation was shown by remarkable accuracy of 97% coupled with outstanding precision, recall and F1-scores including both genders. Low rates of misclassification help to establish even more the dependability of the model by use of the confusion matrix. These results show the viability of the approach and its use in pragmatic gender recognition programs. © 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

Implementation of FIR Digital Filter Algorithm in C Language on DSP Platform

Implementation of FIR Digital Filter Algorithm in C Language...

引用

Information Science, parallel and distributed Systems (ISPDS), International conference on

作者： Guoyong Wang Huaihua Normal College Huaihua China

ISBN: (数字)9798350352719

ISBN: (纸本)9798350352726

This article provides a detailed overview of the process of implementing an FIR digital filter using the TI TMS320 series DSP platform with the C programming language. It covers topics such as the working principle of FIR filters, design methods, DSP development environment setup, C code implementation, simulation verification, and system testing. Through simulation verification, the frequency response characteristics of the FIR filter are confirmed, and the system testing results demonstrate that the FIR filter achieves effective signal filtering under appropriate conditions with accurate frequency response and high signal-to-noise ratio. This document comprehensively validates the excellent signal processing performance of FIR filters on the DSP platform, offering valuable insights for applications involving FIR filter design on DSP platforms.

关键词： Performance evaluation System testing Information science Codes Finite impulse response filters Signal processing algorithms Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Optimus-CC: Efficient Large NLP Model Training with 3D parallelism Aware Communication Compression 2023

Optimus-CC: Efficient Large NLP Model Training with 3D Paral...

引用

28th ACM International conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)

作者： Song, Jaeyong Yim, Jinkyu Jung, Jaewon Jang, Hongsun Kim, Hyung-Jin Kim, Youngsok Lee, Jinho Yonsei Univ Seoul South Korea Seoul Natl Univ Seoul South Korea Samsung Elect Hwaseong South Korea

ISBN: (纸本)9781450399166

In training of modern large natural language processing (NLP) models, it has become a common practice to split models using 3D parallelism to multiple GPUs. Such technique, however, suffers from a high overhead of inter-node communication. Compressing the communication is one way to mitigate the overhead by reducing the inter-node traffic volume;however, the existing compression techniques have critical limitations to be applied for NLP models with 3D parallelism in that 1) only the data parallelism traffic is targeted, and 2) the existing compression schemes already harm the model quality too much. In this paper, we present Optimus-CC, a fast and scalable distributed training framework for large NLP models with aggressive communication compression. Optimus-CC differs from existing communication compression frameworks in the following ways: First, we compress pipeline parallel (inter-stage) traffic. In specific, we compress the inter-stage backpropagation and the embedding synchronization in addition to the existing data-parallel traffic compression methods. Second, we propose techniques to avoid the model quality drop that comes from the compression. We further provide mathematical and empirical analyses to show that our techniques can successfully suppress the compression error. Lastly, we analyze the pipeline and opt to selectively compress those traffic lying on the critical path. This further helps reduce the compression error. We demonstrate our solution on a GPU cluster, and achieve superior speedup from the baseline state-of-the-art solutions for distributed training without sacrificing the model quality.

关键词： distributed Systems Systems for Machine Learning Large-scale NLP Training Pipeline parallelism 3D parallelism Gradient Compression Communication Optimization

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：