检索结果-内蒙古大学图书馆

PERFORMANCE EVALUATION OF BIDIRECTIONAL ASSOCIATIVE MEMORY ON A TRANSPUTER-BASED PARALLEL SYSTEM

PARALLEL COMPUTING 1992年第4期18卷 401-413页

作者： MAHADEVAN, I PATNAIK, LM Dept. of Computer Science and Automation Indian Institute of Science Bangalore 560 012 India Microprocessor Applications Laboratory Supercomputer Education and Research Centre Dept. of Computer Science and Automation Indian Institute of Science Bangalore 560 012 India

In this paper we discuss a parallel implementation of an artificial neural network for pattern association, the Bidirectional Associative Memory (BAM). The parallelism inherent in BAM has been exploited using various transputer-based architectures like hypercube, mesh and linear array. The speedup and utilization of the system are obtained for the architectures mentioned above and a comparative study is made. Simulation results show that the hypercube topology gives a better performance in terms of speedup and utilization when compared to other architectures.

关键词： BIDIRECTIONAL ASSOCIATIVE MEMORY TRANSPUTERS HYPERCUBE MESH LINEAR ARRAY PATTERN RECOGNITION NEURAL NETWORKS

来源：评论

学校读者我要写书评

暂无评论

Strong Baseline with Auto-encoder for Scale-Invariant Person Re-identification 6

Strong Baseline with Auto-encoder for Scale-Invariant Person...

引用

6th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2022

作者： Bilakeri, Shavantrevva Kotegar, Karunakar Manipal Institute of Technology Manipal Academy of Higher Education Dept. of Data Science and Computer Applications Karnataka Manipal India

ISBN: (数字)9781665487160

ISBN: (纸本)9781665487160

Person Re-identification associates the same person images captured by disjoint cameras. The different training strategies and precise hyper-parameter selection are required for the construction of an effective person re-identification. However, in the current work, the tests are carried out by trial and error, which takes a long time to reach an optimal solution. We experiment with various training strategies with the metric learning model serving as the baseline to address this issue. Existing person re-identification benchmarks have insufficient samples for training the ReID model. Also, the previous approaches fail when the same individual appears in varied sizes. To solve this issue, an auto-encoder module is used to create a single image in three distinct scales to enhance the sample size and tackle the scale variation problem of the person reidentification. In addition, a performance comparison is made between the baseline and the baseline with auto-encoder to demonstrate the influence of an auto-encoder as a data augmentation for the person re-identification. The adoption of auto-encoder module and bestperforming training techniques to a baseline have enhanced the rank1 and mAP on Market1501, DukeMTMC-reID datasets. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Comparison and characterization of some selected models on the basis of their suitability for various applications 7

Comparison and characterization of some selected models on t...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Gupta, Kirti Kumar, Pardeep Upadhyaya, Shuchita Kurukshetra University Dept. of Computer Science & Applications Kurukshetra India

ISBN: (纸本)9798350371406

One of the most important aspects of data forecasting is selecting the most promising algorithm to model and predict a specific phenomenon. As with other data mining jobs, forecasting (or prediction) selects the optimal model for a given problem based on empirical evidence because there is no one best modelling technique. Our careful examination of the last ten years' worth of literature indicates that, nevertheless, very few scholarly works thoroughly outline the advantages and drawbacks of the most widely used prediction algorithms. However, these models have a poor track record of success when used on intricate and highly nonlinear data. In this article, we summarise a number of lessons learnt and offer suggestions regarding the benefits, limitations, and ideal circumstances under which to apply each model. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization Based QoS Routing in Mobile Ad Hoc Network: A Mobility Model in Urban Environments 2

Ant Colony Optimization Based QoS Routing in Mobile Ad Hoc N...

引用

2nd IEEE International Conference on Applied Electromagnetics, Signal Processing, and Communication, AESPC 2021

作者： Sarangi, Sanjaya Kumar Panda, Mrutyunjaya Utkal University Dept. of Computer Science and Applications Bhubaneswar India

ISBN: (纸本)9781665442992

Mobile Ad Hoc Network (MANET) is an active multi- hop network formed within the wireless channel with a number of mobile nodes. With major advantages of MANET, it has also complexity in routing because of mobility of the nodes. The complexity is more since it has several characteristics, such as dynamic topology, time differentiated, QoS factors, restricted energy & resources etc. QoS routing provides big challenges to discover a route among the communication systems that meet the client QoS requirements. In this work we are proposing the Ant Colony Optimization Based QoS on-demand routing algorithm which is highly adaptive, effective and scalable. The simulation result shows that the proposed algorithm improves the package delivery ratio & decreases average time-out compared to existing algorithms. © 2021 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A new graph based sequence clustering approach for news article retrieval system

A new graph based sequence clustering approach for news arti...

引用

2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering, ICPCSI 2017

作者： Nagalavi, Deepa Hanumanthappa, M. Dept. of Computer Science and Applications Bangalore University Bangalore India

ISBN: (纸本)9781538608135

During the past few years e-newspapers are becoming more ease and convenience in accessing timely information. It is presented in several independent news articles. The articles are very difficult to understand automatically by system, as the layout of the a newspaper page is geometrically difficult. The goal of the work is to design a system using multi perspective graph clustering algorithm. It creates the clusters of individual article to a very high degree and there should be few occurrence of misplaced articles. © 2017 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2025年

作者： Lee, Ming-Lun Chou, Han-Chang Chen, Yan-Ann Dept. of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan Taiwan

Federated learning is a distributed machine learning framework to collaboratively train a global model without uploading privacy-sensitive data onto a centralized server. Usually, this framework is applied to edge devices such as smartphones, wearable devices, and Internet of Things (IoT) devices which closely collect information from users. However, these devices are mostly battery-powered. The update procedure of federated learning will constantly consume the battery power and the transmission bandwidth. In this work, we propose an update control for federated learning, FedSAUC, by considering the similarity of users’ behaviors (models). At the server side, we exploit clustering algorithms to group devices with similar models. Then we select some representatives for each cluster to update information to train the model. We also implemented a testbed prototyping on edge devices for validating the performance. The experimental results show that this update control will not affect the training accuracy in the long run. © 2025, CC BY-NC-ND.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Detecting Feet's Bending Patterns With Smart Insoles 5

Detecting Feet's Bending Patterns With Smart Insoles

引用

5th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2024

作者： Zhong, Yuchen Ying, Qijun Cai, Xiaohui dept. of Computer Science and Technology Hefei China dept. of Data Science Hefei China

ISBN: (纸本)9798350355925

Foot bending is a basic component of walking. Although bending is important for foot-ground interaction and ensures the speed and balance of the whole walking cycle, there is still no practical method for recording and analyzing foot bending under everyday scenarios. In this study we propose to use a smart insole, with two embedded Inertial Measurement Units, to acquire the movements of the fore-foot and the hind-foot and deduce the bending, represented by the bending point's position. We use the deep learning approach to estimate the bending position and its changes during different walking patterns. On the dataset containing 8 test subjects and 6 walking patterns, our method can achieve an overall mean absolute error accuracy of 2.58 cm. The smart insole can be with the subject all the day, bring in a new method for continuous foot bending monitoring. © 2024 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Lightweight Task-Oriented Semantic Communication Empowered by Large-Scale AI Models

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Chuanhong Guo, Caili Yang, Yang Chen, Mingzhe Quek, Tony Q. S. Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL United States Singapore University of Technology and Design Dept. of Information Systems Technology and Design 487372 Singapore

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant challenges for real-time communication scenarios. To address this, this paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models, effectively reducing model complexity and computation latency. Nevertheless, the inherent complexity of LAI models leads to prolonged inference times during distillation, while their lack of channel awareness compromises the distillation performance. These limitations make standard KD methods unsuitable for task-oriented semantic communication scenarios. To address these issues, we propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference, significantly improving efficiency. Furthermore, a channel adaptive module is incorporated to dynamically adjust the transmitted semantic information based on varying channel conditions, enhancing communication reliability and adaptability. In addition, an information bottleneck-based loss function is derived to guide the fast distillation process. Simulation results verify that the proposed scheme outperform baselines in term of task accuracy, model size, computation latency, and training data requirements. © 1967-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

A Few-Shot Learning for HAR Using 3D Siamese Network 15

A Few-Shot Learning for HAR Using 3D Siamese Network

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Guanghui, Hua Kumar, G. Hemantha Aradhya, V.N. Manjunath Punithavalli University of Mysore Dept. of studies in Computer Science Mysuru India Jss Science and Technology University Dept. of Computer Applications Mysuru India Bharathiar University Department of Computer Applications Coimbatore India

ISBN: (纸本)9798350370249

In artificial intelligence, deep learning techniques were applied in a wide field due to their ability to automatically learn complex patterns from raw data, such as image classification, object detection, image generation, and video analysis in computer vision. These applications are just the tip of a substantial iceberg. With the development of deep techniques to achieve state-of-art accuracy, learn precisely relevant features from raw data, and improve the robustness of models to make them versatile solutions. The traditional deep learning techniques require vast computational resources, including high-performance computer GPUs or TPUs, and can be expensive in terms of hardware. In Human Activity Recognition Systems (HARs). The video needs more computational resources than image processing. In this paper, we proposed a few-shot learning approach based on a 3D Siamese Network with dept. video sequences to address the action video similarity or dissimilar problem. Convolutional Neural Networks (CNNs) are well-suited for images and spatial data processing. The 3DCNN is an extension of CNNs to incorporate an additional temporal dimension to capture the temporal pattern. From the 3D Siamese network, we extract more effective features with spatial-temporal action information from raw data. We employed the 3DCNNs Siamese Network (3DCNNs+SN) with shared weight to recognize or classify a new class of data without new sample data only based on learning training existing sample constructed model. In addition, we divided the benchmark dataset MSR Action 3D dataset into sub-dataset1 (SD-1), sub-dataset2 (SD-2) and sub-dataset3(SD-3) to train and validate our proposed method. For dissimilar sub-dataset 2 we got a 98.1% accuracy, 33% on high-similar sub-dataset 3 and 63.5% on merged sub-dataset SD-4 from sub-dataset2 (SD-2) and sub-dataset3(SD-3). © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Energy efficient next-gen of virtualization for cloud-native applications in modern data centres 4

Energy efficient next-gen of virtualization for cloud-native...

引用

4th International Conference on IoT in Social, Mobile, Analytics and Cloud, ISMAC 2020

作者： Bharani Dharan, G. Jayalakshmi, S. VISTAS Dept. of Computer Science Pallavara Chennai India VISTAS Dept. of Computer Applications Pallavaram Chennai India

ISBN: (纸本)9781728154640

In the new software-driven world this is the need of the hour to achieve success by accelerating development, delivery of applications and services rapidly that make customers happy and business competitive. To achieve faster delivery of resources and applications to strengthen the business with more transformations containers have been introduced. At the existing scenario, the hyper-converged data centre uses the concept of virtualization which creates software abstraction of the underlying hardware using Hypervisor software that enables to execute several Virtual Machines (VMs) with dissimilar Operating System (OS) flavours. But virtualization is heavyweight and it may take more time to boot. The proposed containerization and docker in hybrid cloud composable data centre is lightweight supports Operating System (OS) level virtualization that isolates resources, libraries and other binaries bundled into a single package for agile modern scalable workloads. This paper focuses on the container-based virtualization to shape the future cloud-based modern data centre for supporting the micro-services based applications for faster deployment to Developer Operations (DevOps) teams in IT with resiliency, High Availability and better resource management with energy savings. © 2020 IEEE.

关键词： Containers

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：