检索结果-内蒙古大学图书馆

2024 International Conference on Advanced Technologies for Communications, ATC 2024

作者： Chen, Yen-Yi Wang, Jian-Hong Chan, Po-Cheng Liang, Kai-Wen Wang, Ze-Yu Wang, Jia-Ching School of Computer Science and Technology Shandong University of Technology Shandong Zibo China National Central University Department of Computer Science and Information Engineering Taoyuan Taiwan Advanced Technology Laboratory Chunghwa Telecom Laboratories Taiwan

ISBN: (纸本)9798350353983

This paper presents an innovative approach to acoustic echo cancellation (AEC) by applying Variable Step Size (VSS) separately to each adaptive filtering technique: Normalized Least Mean Square (NLMS), and Proportionate Normalized Least Mean Square (PNLMS). This application is tailored to overcome the challenges of step size adjustment and signal sparsity, significantly enhancing system performance. We demonstrate that utilizing VSS with each algorithm independently allows for optimized control over convergence rates-larger step sizes quicken convergence while smaller sizes ensure smoother transitions. This method improves the robustness and efficiency of echo cancellation systems, removing the need for manual step size adjustments and proving highly effective in real-time applications. © 2024 IEEE.

关键词： Echo suppression

来源：评论

学校读者我要写书评

暂无评论

Smart Job Scheduling Model for Cloud Computing Network Application

引用

SN computer science 2024年第1期5卷 39页

作者： Onyema, Edeh Michael Gude, Venkataramaiah Bhatt, Ashutosh Aggarwal, Ambika Kumar, Sunil Benson-Emenike, Mercy Eberechi Nwobodo, Lois Onyejere Department of Vocational and Technical Education Faculty of Education Alex Ekwueme Federal University Ndufu-Alike Abakaliki Nigeria Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India GP Technologies LLC Texas United States Department of Computer Science and Engineering Shivalik College of Engineering Dehradun India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Computer Science Federal University of Technology Owerri Nigeria Department of Computer Engineering Enugu State University of Science and Technology Enugu Nigeria

Task scheduling is one of the significant factors for heterogeneous type of elements in multi-cloud computing environment. It is to delegate activities to most adequate resources to raise the performance with respect to some dynamic parameters. The suggested model of scheduling was designed to run applications of cloud computing which applied in three steps (classifying, execution, minimization, and rating) and is assumed to be completion time, average waiting and turnaround time, and render duration as output parameters. The tasks’ execution time in cloud computing applications was created in the task scheduling model by exponential and normal distribution. The task ranking depends on the shortest strategy for First Job and the results are compared with other “Largest Processing Time” and “First Come First Serve” ranking method. Scheduling model proposed provides significant output than per performance parameters specified. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cloud computing Directed acyclic graph (DAG) Smart scheduling

来源：评论

学校读者我要写书评

暂无评论

Joint user profiling with hierarchical attention networks

引用

Frontiers of computer science 2023年第3期17卷 133-143页

作者： Xiaojian LIU Yi ZHU Xindong WU Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology) Ministry of EducationHefei 230009China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China School of Information Engineering Yangzhou UniversityYangzhou 225009China Mininglamp Academy of Sciences MininglampBeijing 100193China

User profiling by inferring user personality traits,such as age and gender,plays an increasingly important role in many real-world *** existing methods for user profiling either use only one type of data or ignore handling the noisy information of ***,they usually consider this problem from only one *** this paper,we propose a joint user profiling model with hierarchical attention networks(JUHA)to learn informative user representations for user *** JUHA method does user profiling based on both inner-user and inter-user *** explore inner-user features from user behaviors(e.g.,purchased items and posted blogs),and inter-user features from a user-user graph(where similar users could be connected to each other).JUHA learns basic sentence and bag representations from multiple separate sources of data(user behaviors)as the first round of data *** this module,convolutional neural networks(CNNs)are introduced to capture word and sentence features of age and gender while the self-attention mechanism is exploited to weaken the noisy *** this,we build another bag which contains a user-user ***-user features are learned from this bag using propagation information between linked users in the *** acquire more robust data,inter-user features and other inner-user bag representations are joined into each sentence in the current bag to learn the final bag ***,all of the bag representations are integrated to lean comprehensive user representation by the self-attention *** experimental results demonstrate that our approach outperforms several state-of-the-art methods and improves prediction performance.

关键词： user profiling hierarchical attention joint learning inner-user feature inter-user feature

来源：评论

学校读者我要写书评

暂无评论

Investigating Decentralized Governance Models for Crypto currency Networks 15

Investigating Decentralized Governance Models for Crypto cur...

引用

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

作者： Seth, Jyoti Sudhamsu, Gadug Garg, Richa Vivekananda Global University Department of Computer Science & Engineering Jaipur India School of Engineering and Technology Department of Computer Science and Engineering Karnataka Bangalore India Arka Jain University Department of Management Jharkhand Jamshedpur India

ISBN: (纸本)9798350370249

Decentralized governance fashions for crypto currency networks provide a manner to set up a machine of protocol bylaws and rules that govern the network. those models rely on a consensus-based totally set of rules that enables a distributed machine of nodes, inclusive of miners, software builders, and users, to make decisions about how the community have to function. The intention of decentralized governance for crypto foreign money networks is to offer a reliable way of controlling protocol enhancements, community guidelines, and roles. Decentralized governance models can assist maximize credibility, decentralization, and security whilst minimizing the hazard of centralization and the capability for misbehavior. Similarly, the decentralized technique to crypto forex networks allows users to take a greater active function in establishing policies and protocols for their networks. This study reviews specific decentralized governance fashions, their capability applications, and their benefits and downsides. It also seems at latest traits toward implementing such models on distinct crypto forex networks. Sooner or later, they have a look at discusses key demanding situations and possibilities for a hit and at ease implementation of decentralized governance models for crypto foreign money networks. © 2024 IEEE.

关键词： Community Currency Decentralized Distributed Enhancements Establishing Technique

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Artificial Intelligence Framework to Forecast the Security Index Direction and Value in Fusion with Sentiment Analysis of Financial News

引用

SN computer science 2024年第6期5卷 787页

作者： Singh, Harmanjeet Malhotra, Manisha Singh, Supreet Sharma, Preeti Prabha, Chander University School of Computing Rayat Bahra University University Institute of Computing Chandigarh University School of Computer Science UPES Chitkara University Institute of Engineering and Technology Chitkara University

The domain of stock price prediction is extensively researched owing to its complex data structure and numerous influential factors. In the current epoch, many modern financial applications demonstrate non-linear and uncertain characteristics that exhibit temporal variability. As a result, there has been a notable rise in the need for resolutions to highly non-linear and time-variant issues. External factors, including public sentiment and political events, can influence stock market trends. The primary aim of this research is to propose a novel framework for predicting the blue-chip stock price in the future by combining historical stock data corresponding to the financial news published regarding stock in the newspaper. The initial step involves integrating sentiment and situational features into a machine-learning model. This integration aims to evaluate public sentiments’ influence on algorithms’ predictive precision thirty days ahead. Furthermore, regression models are utilized to analyze the inter-dependencies that exist among companies. To facilitate an experimental analysis, the researchers acquired historical data from the stock market through reputable sources such as the National Stock Exchange-India and collected news data about stock from the financial newspaper “EconomicTimes”. A series of machine learning models were tested to facilitate the classification of news sentiments of the stocks, followed by the fusion of resultant polarities with the stock’s historical data on the standard column “DATE” and then tested series of deep learning models to observe the impact of news on stock price and by taking reference of this, the authors successfully predicted the stock price on a random day. The findings unequivocally indicate that the proposed research design produces better results than other state-of-the-art models. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Comparative analysis Economics Sentiment analysis Stock news Stock price forecast

来源：评论

学校读者我要写书评

暂无评论

Modeling Methods of 3D Model in Digital Twins

引用

computer Modeling in engineering & sciences 2023年第8期136卷 985-1022页

作者： Ruijun Liu Haisheng Li Zhihan Lv School of Computer Science and Engineering Beijing Technology and Business UniversityBeijing100080China Department of Game Design Faculty of ArtUppsala UniversityUppsalaS-75105Sweden

To understand the current application and development of 3D modeling in Digital Twins(DTs),abundant literatures on DTs and 3D modeling are investigated by means of literature *** transition process from 3D modeling to DTs modeling is analyzed,as well as the current application of DTs modeling in various *** application of 3D DTs modeling in the􀀀elds of smartmanufacturing,smart ecology,smart transportation,and smart buildings in smart cities is analyzed in detail,and the current limitations are *** is found that the 3D modeling technology in DTs has broad prospects for development and has a huge impact on all walks of life and even human *** the same time,the development of DTs modeling relies on the development and support capabilities of mature technologies such as Big Data,Internet of Things,Cloud Computing,Articial Intelligence,and game ***,although some results have been achieved,there are still *** work aims to provide a good theoretical support for the further development of 3D DTs modeling.

关键词： Digital twins 3D modeling smart manufacturing smart city smart buildings

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Knowledge Graph for Recommendation via Invariant Learning 24

Unleashing the Power of Knowledge Graph for Recommendation v...

引用

33rd ACM Web Conference, WWW 2024

作者： Wang, Shuyao Sui, Yongduo Wang, Chao Xiong, Hui School of Data Science University of Science and Technology of China China Hong Kong The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Guangzhou Hkust Fok Ying Tung Research Institute Hong Kong

ISBN: (纸本)9798400701719

Knowledge graph (KG) demonstrates substantial potential for enhancing the performance of recommender systems. Due to its rich semantic content and associations among interactive entities, it can effectively alleviate inherent limitations in collaborative filtering (CF), such as data sparsity or cold-start issues. However, most existing knowledge-aware recommendation models indiscriminately aggregate all information in KG, without considering information specifically relevant to the recommendation task. Such indiscriminate aggregation could introduce additional noisy knowledge into representation learning, which can distort the understanding of users' genuine preferences, thereby sacrificing the recommendation quality. In this paper, we introduce the principle of invariance to the knowledge-aware recommendation, culminating in our Knowledge Graph Invariant Learning (KGIL) framework. It aims to discern and harness the task-relevant knowledge connections within KG to enhance the recommendation models. Specifically, we employ multiple environment generators to simulate diverse noisy KG-environments. Then we devise a novel attention learning mechanism for KG and user-item interaction graph, aiming to learn environment-invariant subgraphs. Leveraging an adversarial optimization strategy, we enhance the diversity of the environments, meanwhile, promote invariant representation learning across environments. We conduct extensive experiments on three datasets and compare KGIL with state-of-the-art methods. The experimental results further demonstrate the superiority of our approach. © 2024 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Optimized Deep Learning Classification Model for Intelligent Edge devices

引用

Journal of engineering science and technology Review 2024年第3期17卷 88-94页

作者： Naveen, Soumyalatha Kounte, Manjunath R Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal India School of Electronics and Communication Engineering REVA University Karnataka Bangalore560064 India

Deep learning models enable state-of-the-art accuracy in computer vision applications. However, the deeper, computationally expensive, and densely connected architecture of deep neural networks (DNN) have limitations for deploying the model on resource-constraint embedded IoT devices. We propose an efficient neural network compression framework that performs filter pruning, fine-tuning and 8-bit quantization to reduce computational complexity, inference time, and memory footprint. Furthermore, reducing the bit widths of activation and weights helps design a compact deployment model on resource-limited IoT devices such as smartphones. The proposed system is evaluated extensively on the CIFAR-10 dataset for Resnet34 and VGG16 models. In addition, we examine the efficacy of a larger model. The result shows that pruning followed by quantization compresses the neural network and compared to the baseline model, achieved an accuracy of 78.01% for Resnet34 and 82.34% for Vgg16 after pruning and quantization which is © 2024 school of science, DUTH. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Attitude Controller for A Quadrotor Transporting the Payload With Unknown Mass 38

An Adaptive Attitude Controller for A Quadrotor Transporting...

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Qiu, Shihao Chen, Longlong Li, Shuang Lv, Zongyang Tang, Huayi Dalian University of Technology School of Computer Science and Technology Dalian China Dalian University of Technology School of Control Science and Engineering Dalian China Henan University of Technology College of Information Science and Engineering Zhengzhou China Dalian University of Technology School of Mechanical Engineering Dalian China

ISBN: (纸本)9798350303636

An adaptive control approach is presented in this article to deal with the impacts of carrying a payload with unknown mass by a quadrotor. This approach can effectively control the quadrotor's attitude stability. The paper commences by presenting the dynamic model of the quadrotor, followed by the development of a controller to manage its attitude control. Through Lyapunov analysis, the stability of the controller is validated. Ultimately, the proposed controller and a backstepping controller are used to controlling the attitude of the quadrotor, respectively, and experimental outcomes substantiate the efficiency and feasibility of the introduced controller. © 2023 IEEE.

关键词： Adaptive Control Quadrotor Unmanned Aerial Vehicle Unknown Mass Payload

来源：评论

学校读者我要写书评

暂无评论

Spatial-temporal Dynamic Forecasting of EVs Charging Load Based on DCC-2D

引用

Chinese Journal of Electrical engineering 2022年第1期8卷 53-62页

作者： Shurong Peng Heng Zhang Yunhao Yang Bin Li Sheng Su Shijun Huang Guodong Zheng School of Electrical&Information Engineering Changsha University of Science&TechnologyChangsha 410114China College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China

The charging load of electric vehicles(EVs)has a strong spatiotemporal *** the dynamic spatiotemporal distribution of the charging load of EVs is of great significance for the grid to cope with the access of large-scale *** studies lack a prediction model that can accurately describe the dual dynamic changes of EVs charging the load time and ***,a spatial-temporal dynamic load forecasting model,dilated causal convolution-2D neural network(DCC-2D),is ***,a hole factor is added to the time dimension of the three-dimensional convolutional convolution kernel to form a two-dimensional hole convolution layer so that the model can learn the spatial dimension *** entire network is then formed by stacking the layers,ensuring that the network can accept long-term historical input,enabling the model to learn time dimension *** model is simulated with the actual data of the charging pile load in a certain area and compared with the ConvLSTM *** results prove the validity of the proposed prediction model.

关键词： Time and space dynamic prediction dilated convolution charging load convolutional neural network

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：