检索结果-内蒙古大学图书馆

29th International Conference on Parallel and distributed Computing (Euro-Par)

作者： Ibrahim, Abdul Qadir Goetschel, Sebastian Ruprecht, Daniel Hamburg Univ Technol Inst Math Chair Computat Math Hamburg Germany

ISBN: (纸本)9783031396977;9783031396984

Parallel-in-time algorithms provide an additional layer of concurrency for the numerical integration of models based on time-dependent differential equations. Methods like Parareal, which parallelize across multiple time steps, rely on a computationally cheap and coarse integrator to propagate information forward in time, while a parallelizable expensive fine propagator provides accuracy. Typically, the coarse method is a numerical integrator using lower resolution, reduced order or a simplified model. Our paper proposes to use a physics-informed neural network (PINN) instead. We demonstrate for the Black-Scholes equation, a partial differential equation from computational finance, that Parareal with a PINN coarse propagator provides better speedup than a numerical coarse propagator. Training and evaluating a neural network are both tasks whose computing patterns are well suited for GPUs. By contrast, mesh-based algorithms with their low computational intensity struggle to perform well. We show that moving the coarse propagator PINN to a GPU while running the numerical fine propagator on the CPU further improves Parareal's single-node performance. This suggests that integrating machine learning techniques into parallel-in-time integration methods and exploiting their differences in computing patterns might offer a way to better utilize heterogeneous architectures.

关键词： Parareal parallel-in-time integration PINN Machine learning GPUs heterogeneous architectures

来源：评论

学校读者我要写书评

暂无评论

Edge/Cloud Slice Resource Allocation for Beyond 5G networks With distributed LSTM 35

Edge/Cloud Slice Resource Allocation for Beyond 5G Networks ...

引用

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Ehsanian, Ali Spyropoulos, Thrasyvoulos Eurecom Sophia-Antipolis France Technical University of Crete Chania Greece

ISBN: (纸本)9798350362244

Efficient resource allocation among slices/users with different Service Level Agreements (SLAs) is a critical task in 5G+ networks, which has prompted recent research into Deep neural networks (DNNs). However, challenges arise when dealing with edge resources, including the ability to rapidly scale resources (in the order of milliseconds), and the cost of transmitting large data volumes to a cloud for centralized DNN-based processing. Addressing these issues, we introduce a novel architecture based on distributed Deep neural networks (DDNN). This architecture features a compact set of DNN layers located at the network's edge, designed to function as an autonomous resource allocation unit. Complementing this, there is an intelligent offloading mechanism that delegates a fraction of hard decisions to additional DNN layers situated in a remote cloud (when needed). To implement offloading, we propose a theoretically informed method that learns to mimic an oracle that knows which sample will benefit from additional processing in the cloud. We compare this to a previously proposed heuristic, based on a Bayesian-confidence mechanism. We investigate the interplay of (offline) joint training of the DDNN exits and the ML-based offloading mechanism, and demonstrate that our architecture resolves more than 50% of decisions at the edge with no additional penalty compared to centralized models as well as consistently outperforms previous methods. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Brand Logo Image Classification Based on Deep Convolutional Generative Adversarial network 3

Brand Logo Image Classification Based on Deep Convolutional ...

引用

3rd IEEE International Conference on distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Wang, Yang Guangzhou Institute Of Science Technology Guangzhou China

ISBN: (纸本)9798350318609

Brand logo image examines how a critical dimension of logo design, namely the naturalness of the logo color, influences brand design induced by the logo. However, high complexity is observed, requiring higher quality data and susceptibility to overfitting when there is insufficient training data. The implementation of the proposed system involved the utilization of a Deep Convolutional Generative Adversarial network (DCGAN) reduce overfitting and efficiently handle noise and distortion in the logo image, which is essential in brand logo image processing. The brand logo image dataset forwarded to the preprocessing stage included pixel values, which may lead to the loss of contrast, shadow, sharpness, noise removal, and structure in some relevant images. The classification involved DCGAN, aiming to achieve high-quality logo image prediction, noise reduction, and handling of overfitting by incorporating synthetic logo images. The proposed DCGAN method achieves promising performance, including a mean Average Precision (mAP) of 52.25, Accuracy of 97.09%, Precision of 97.01 %, Recall of 98.10%, and F1-score of 97.11 %. This performance is compared to existing methods such as YOLOv3 and Convolutional neural network (CNN) - Long Short-Term Memory (LSTM). © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Dystri: A Dynamic Inference based distributed DNN Service Framework on Edge 23

Dystri: A Dynamic Inference based Distributed DNN Service Fr...

引用

52nd International Conference on Parallel processing (ICPP)

作者： Hou, Xueyu Guan, Yongjie Han, Tao New Jersey Inst Technol Newark NJ 07102 USA

ISBN: (纸本)9798400708435

Deep neural network (DNN) inference poses unique challenges in serving computational requests due to high request intensity, concurrent multi-user scenarios, and diverse heterogeneous service types. Simultaneously, mobile and edge devices provide users with enhanced computational capabilities, enabling them to utilize local resources for deep inference processing. Moreover, dynamic inference techniques allow content-based computational cost selection per request. This paper presents Dystri, an innovative framework devised to facilitate dynamic inference on distributed edge infrastructure, thereby accommodating multiple heterogeneous users. Dystri offers a broad applicability in practical environments, en-compassing heterogeneous device types, DNN-based applications, and dynamic inference techniques, surpassing the state-of-the-art (SOTA) approaches. With distributed controllers and a global coordinator, Dystri allows per-request, per-user adjustments of qualityof-service, ensuring instantaneous, flexible, and discrete control. The decoupled workflows in Dystri naturally support user heterogeneity and scalability, addressing crucial aspects overlooked by existing SOTA works. Our evaluation involves three multi-user, heterogeneous DNN inference service platforms deployed on distributed edge infrastructure, encompassing seven DNN applications. Results show Dystri achieves near-zero deadline misses and excels in adapting to varying user numbers and request intensities. Dystri outperforms baselines with accuracy improvement up to 95x.

关键词： MLaaS dynamic inference edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Small Object Detection in Aerial Imagery Based on Strong Feature Extraction and Batch Dimension

Enhancing Small Object Detection in Aerial Imagery Based on ...

引用

International Joint Conference on neural networks (IJCNN)

作者： Cao, Bingnan Wang, Di Guo, Ying Zhang, Hu Qilu Univ Technol Shandong Comp Sci Ctr Natl Supercomp Ctr Jinan Key Lab Comp Power Network & Informat Secur Minist EducShandong Acad Sci Jinan Peoples R China Shandong Fundamental Res Ctr Comp Sci Shandong Prov Key Lab Comp Networks Jinan Peoples R China City Univ Macau Inst Data Sci Macau Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Object detection is a fundamental component of computer vision, playing a pivotal role in various applications. However, the accurate detection of small and densely distributed objects remains a challenging problem in this field. This challenge is particularly exacerbated in the context of aerial imagery, characterized by its distinctive bird's-eye view, intricate backgrounds, and the variability in object appearances. This paper addresses these persistent challenges in object detection, with a focus on the specific difficulties posed by aerial images. We propose a deformable end-to-end object detection with transformers (DETR)-based framework to enhance small object detection accuracy, ultimately contributing to improved computer vision capabilities in domains like remote sensing, surveillance, and autonomous aerial systems. Firstly, in order to aggregate the entire input sequence information in the backbone network and improve the detection accuracy of small objects, we propose DMCA based on deformable features and attention mechanisms. Secondly, in order to capture and model the relationships between samples for dense pixel-level representations in small objects and improve the detection accuracy of small objects, we try to introduce BatchEncoder by implementing an encoder in the batch dimension. Experimental results show that, compared to the baseline, our method significantly improves the accuracy of small object detection in aerial images. The processing and analysis of a large amount of remote sensing data require powerful computing power. The computing power Internet can integrate the scattered computing resources to provide flexible and scalable computing power to meet the computing needs of different sizes and types.

关键词： small object detection remote sensing DMCA(Deformable Multiscale Channel Attention) BatchEncoder

来源：评论

学校读者我要写书评

暂无评论

LMR-CBT: learning modality-fused representations with CB-Transformer for multimodal emotion recognition from unaligned multimodal sequences

引用

Frontiers of Computer Science 2024年第4期18卷 39-47页

作者： Ziwang FU Feng LIU Qing XU Xiangling FU Jiayin QI School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Beijing 100876China Shanghai International School of Chief Technology Officer East China Normal UniversityShanghai 200062China School of Computer Science and Technology East China Normal UniversityShanghai 200062China School of Cyberspace Security Guangzhou UniversityGuangdong 510006China

Learning modality-fused representations and processing unaligned multimodal sequences are meaningful and challenging in multimodal emotion *** approaches use directional pairwise attention or a message hub to fuse language,visual,and audio ***,these fusion methods are often quadratic in complexity with respect to the modal sequence length,bring redundant information and are not *** this paper,we propose an efficient neural network to learn modality-fused representations with CB-Transformer(LMR-CBT)for multimodal emotion recognition from unaligned multi-modal ***,we first perform feature extraction for the three modalities respectively to obtain the local structure of the ***,we design an innovative asymmetric transformer with cross-modal blocks(CB-Transformer)that enables complementary learning of different modalities,mainly divided into local temporal learning,cross-modal feature fusion and global self-attention *** addition,we splice the fused features with the original features to classify the emotions of the ***,we conduct word-aligned and unaligned experiments on three challenging datasets,IEMOCAP,CMU-MOSI,and *** experimental results show the superiority and efficiency of our proposed method in both *** with the mainstream methods,our approach reaches the state-of-the-art with a minimum number of parameters.

关键词： modality-fused representations cross-model blocks multimodal emotion recognition unaligned multimodal sequences computational affection

来源：评论

学校读者我要写书评

暂无评论

Research on distributed cooperative silicon based photonic computing chip 4

Research on distributed cooperative silicon based photonic c...

引用

4th International Conference on Electronic Information Engineering and Computer Communication, EIECC 2024

作者： Zhu, Kejian Li, Tuo Wang, Changhong Wang, Menglong Zou, Xiaofeng Sun, Pengfei Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co. Ltd. Shandong Jinan China Peking University School of Electronics Beijing China

ISBN: (纸本)9798331534622

In this paper, an architecture of a photonic neural network chip with distributed multi-scenarios is presented. The distributed computing chip has five computing modules, which are characterized by three-dimensional imaging processing, convolutional operation, matrix operation, low-energy operation, and high-speed operation, respectively. Through the cooperative work of multiple modules, self-adaptive high-speed and energy-efficient computation of large-scale computing tasks can be realized. © 2024 IEEE.

关键词： Photonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

distributed Device-Specific Anomaly Detection using Deep Feed-Forward neural networks 36

Distributed Device-Specific Anomaly Detection using Deep Fee...

引用

36th IEEE/IFIP network Operations and Management Symposium, NOMS 2023

作者： Lübben, Christian Pahl, Marc-Oliver Technical University of Munich Germany Imt Atlantique France

ISBN: (纸本)9781665477161

The Internet of Things (IoT) requires sophisticated security measures because of heterogeneity and resource constraints. Current approaches in Anomaly Detection (AD) do not meet both challenges. Device-specific AD models can account for the heterogeneity of devices. However, existing approaches fail to run on constrained devices. This paper presents the approach of distributed device-specific AD models. Each model processes only data from one device. Through this simplification of the prediction task, lightweight AD models can be created. They provide the ability to counter the resource constraints of devices. With less requirements in processing power, IoT devices can perform AD on their own. The novel approach improves the optimization metrics detection performance, latency, and model complexity. The evaluation uses the publicly available UNSW-NB15 dataset. It shows that models can be simplified to run on IoT devices. Measurements with a device-specific model on a Raspberry PI show only a little increase in training and processing time compared to central processing on a desktop PC. While the accuracy maintains >98%, the F1-score increases from 0.64 up to 0.89 in the distributed approach. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Pavlovian Conditioning Modeling Using Wireless Spiking neural network 20

Pavlovian Conditioning Modeling Using Wireless Spiking Neura...

引用

20th International SoC Design Conference (ISOCC)

作者： Lin, Jiaying Nagazawa, Ryuji Kien Nguyen Sekiya, Hiroo Torikai, Hiroyuki Hasegawa, Mikio Hwang, Won-Joo Chiba Univ Grad Sch Sci & Engn Chiba Chiba 2638522 Japan Hosei Univ Grad Sch Sci & Engn Koganei Tokyo 1848584 Japan Tokyo Univ Sci Fac Engn Grad Sch Sinjuku Tokyo 1258585 Japan Pusan Natl Univ Dept Informat Convergence Engn Artificial Intelli Busan 46241 South Korea

ISBN: (纸本)9798350327038

To address the communication congestion and high energy consumption issues in IoT networks, prior research has proposed a distributed information processing system called WiBIC. As an exploratory step towards implementing the basic functionalities of the WiBIC system, this study focuses on the wireless integration of SNNs. Considering the data transmission and learning characteristics of SNNs, we propose using the APCMA protocol to effectively stabilize the operation of the wireless SNN. By modeling Pavlovian conditioning on this network, the learning capabilities of the implemented system can be determined.

关键词： Spiking neural network wireless communication

来源：评论

学校读者我要写书评

暂无评论

Accuracy evaluation of supervised machine learning classification models for wireless network traffic

引用

INTERNATIONAL JOURNAL OF COMMUNICATION networkS AND distributed SYSTEMS 2022年第6期28卷 655-678页

作者： Grabs, Elans Petersons, Ernests Efrosinin, Dmitry Ipatovs, Aleksandrs Kluga, Janis Sturm, Valentin Riga Tech Univ Telecommun Inst Azenes St LV-1048 Riga Latvia Johannes Kepler Univ Linz Inst Stochast Altenberger Str 69 A-4040 Linz Austria

The article contains results of training and testing machine learning models with captured network traffic data. The main goal is to perform classification of video traffic in computer networks. Multiple performance metrics have been evaluated for commonly used classic supervised machine learning algorithms, as well as more advanced convolutional neural network model (for comparison). The article describes in detail the experimental setup, traffic pre-processing procedure, features extraction with different traffic window length and model parameters for training/testing. The article provides some experimental results in the form of tables and 3D surface plots. The conclusion of the article summarises the main findings and outlines the future study directions.

关键词： accuracy classification models features extraction network traffic performance metrics statistical parameters supervised machine learning traffic intensity window length wireless networks convolutional neural network CNN

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：