检索结果-内蒙古大学图书馆

Low-cost video-based air quality estimation system using structured deep learning with selective state space modeling

引用

Environment International 2025年 199卷 109496页

作者： Ahmed, Maqsood Zhang, Xiang Shen, Yonglin Ahmed, Tanveer Ali, Shahid Ali, Ayaz Gulakhmadov, Aminjon Nam, Won-Ho Chen, Nengcheng National Engineering Research Center of Geographic Information System School of Geography and Information Engineering China University of Geosciences Wuhan430074 China Department of Computer Science School of Engineering and Digital Sciences Nazarbayev University Astana Kazakhstan Software College Northeastern University Shenyang110169 China Department of Cybernetics Nanotechnology and Data Processing Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44-100 Poland Research Center of Ecology and Environment in Central Asia Xinjiang Institute of Ecology and Geography Chinese Academy of Sciences Urumqi830011 China Institute of Water Problems Hydropower and Ecology of the National Academy of Sciences of Tajikistan Dushanbe734042 Tajikistan School of Social Safety and Systems Engineering Institute of Agricultural Environmental Science National Agricultural Water Research Center Hankyong National University Anseong Korea Republic of

Air quality is crucial for both public health and environmental sustainability. An efficient and cost-effective model is essential for accurate air quality predictions and proactive pollution control. However, existing research primarily focuses on single static image analysis, which does not account for the dynamic and temporal nature of air pollution. Meanwhile, research on video-based air quality estimation remains limited, particularly in achieving accurate multi-pollutant outputs. This study proposes Air Quality Prediction-Mamba (AQP-Mamba), a video-based deep learning model that integrates a structured Selective State Space Model (SSM) with a selective scan mechanism and a hybrid predictor (HP) to estimate air quality. The spatiotemporal forward and backward SSM dynamically adjusts parameters based on input, ensures linear complexity, and effectively captures long-range dependencies by bidirectional processing of spatiotemporal features through four scanning techniques (row-wise, column-wise, and their vertical reversals), which allows the model to accurately track pollutant concentrations and air quality variations over time. Thus, the model efficiently extracts spatiotemporal features from video and simultaneously performs regression (PM2.5, PM10, and AQI), and classification (AQI) tasks, respectively. A high-quality outdoor hourly air quality dataset (LMSAQV) with 13,176 videos collected from six monitoring stations in Lahore, Pakistan, was utilized as the case study. The experimental results demonstrate that the AQP-Mamba significantly outperforms several state-of-the-art models, including VideoSwin-T, VideoMAE, I3D, VTHCL, and TimeSformer. The proposed model achieves strong regression performance (PM2.5: R2 = 0.91, PM10: R2 = 0.90, AQI: R2 = 0.92) and excellent classification metrics: accuracy (94.57 %), precision (93.86 %), recall (94.20 %), and F1-score (93.44 %), respectively. The proposed model delivers consistent, real-time performance with a latency

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

A business model for video transmission services using dynamic adaptation streaming over HTTP 9

A business model for video transmission services using dynam...

引用

9th Advanced International Conference on Telecommunications, AICT 2013

作者： Rodríguez, Demóstenes Zegarra Rosa, Renata Lopes Bressan, Graça Laboratory of Computer Architecture and Networks Computer and Digital System Engineering Department University of São Paulo São Paulo Brazil

ISBN: (纸本)9781612082790

A business model for video transmission services is proposed that uses the Dynamic Adaptation Streaming over HTTP (DASH) mechanism using different versions of the same video. These video versions are encoded using different parameters, such as spatial resolution or number of frames per second. The transmission of each video version depends on the capabilities of the network at the end user point. The business model proposed considers different costs for each version of video fragments transmitted. The costs of video resolution upgrade are predefined by the service provider and used during the video streaming. Also, in this model, the user can either accept or reject an upgrade. Subjective tests were performed using different spatial resolutions of the same video, in which the interest level of users to perform a video upgrade is evaluated. Furthermore, the network architecture of the proposed solution is presented and the technical feasibility to deploy the proposed solution in commercial networks is shown. As a consequence, the proposed solution can improve the earnings of the video service provider. Copyright © 2013 IARIA.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Cluster-preserving sampling algorithm for large-scale graphs

引用

Science China(Information Sciences) 2023年第1期66卷 60-76页

作者： Jianpeng ZHANG Hongchang CHEN Dingjiu YU Yulong PEI Yingjun DENG National Digital Switching System E&T Research Center Information Engineering University Network Systems Department of the Strategic Support Force School of Computer Science and Technology Eindhoven University of Technology Center for Applied Mathematics Tianjin University

Graph sampling is a very effective method to deal with scalability issues when analyzing largescale graphs. Lots of sampling algorithms have been proposed, and sampling qualities have been quantified using explicit properties(e.g., degree distribution) of the sample. However, the existing sampling techniques are inadequate for the current sampling task: sampling the clustering structure, which is a crucial property of the current networks. In this paper, using different expansion strategies, two novel top-leader sampling methods(i.e., TLS-e and TLS-i) are proposed to obtain representative samples, and they are capable of effectively preserving the clustering structure. The rationale behind them is to select top-leader nodes of most clusters into the sample and then heuristically incorporate peripheral nodes into the sample using specific expansion strategies. Extensive experiments are conducted to investigate how well sampling techniques preserve the clustering structure of graphs. Our empirical results show that the proposed sampling algorithms can preserve the population's clustering structure well and provide feasible solutions to sample the clustering structure from large-scale graphs.

关键词： graph sampling clustering structure top-leader nodes expansion strategies large-scale graphs

来源：评论

学校读者我要写书评

暂无评论

Steady rollback and recovery policy based on integrity measurement

Steady rollback and recovery policy based on integrity measu...

引用

2010 IEEE International Conference on Intelligent Computing and Intelligent systems, ICIS 2010

作者： Xu, Mingdi Zhao, Heng Li, Junlin Zhang, Huanguo System Software Department Wuhan Digital Engineering Institute Wuhan China School of Computer Wuhan University Wuhan China

ISBN: (纸本)9781424465835

As to distributed processing environment, the intractable problem is that process's current state is indeterminate, which could bring some security issues such as diffusing action. We put forward a checkpoint of integrity measurement (CPIM) arithmetic. The CPIM arithmetic could control process's state when process encounters an integrity measurement checkpoint, which would solve the problem that the running state of parallel software is indeterminate. The virtue of CPIM arithmetic is simple and low-cost. We also provide implementation scheme and prototype for evaluating overhead and performance. ©2010 IEEE.

关键词： Integrity measuremtn Recovery Rollback

来源：评论

学校读者我要写书评

暂无评论

Safety concerns on operating UAV using cooperative multiagent negotiation

Safety concerns on operating UAV using cooperative multiagen...

引用

作者： Corrêa, Mário A. Camargo Jr., João B. Gimenes, Ricardo A.V. Almeida Jr., Jorge R. Safety Analysis Group of Computer Digital System Engineering Department University of São Paulo São Paulo Brazil

ISBN: (纸本)8587978128

Abstract Developed countries have made significant efforts to integrate UAV operations in controlled aerial space due to a rising interest of using Unmanned Aerial Vehicles (UAV) for civilian purposes. This study focuses the use of multi-agent architecture to distribute the workload of detecting and solving conflicts between the aircraft and the UAV with no intervention from ground-based facilities. Midair collision risk was the main unsafe situation evaluated using an aircraft collision model based on air traffic density data. Copyright © 2006 IFAC.

关键词： Air traffic control

来源：评论

学校读者我要写书评

暂无评论

Metadata in digital video repositories: An analysis on author-generated metadata

Metadata in digital video repositories: An analysis on autho...

引用

2010 International Conference on Information Society, i-Society 2010

作者： Dantas, Joana Socrates Silveira, Regina Melo Ruggiero, Wilson Vicente LARC-Laboratory of Computer Architecture and Networks Department of Computer and Digital System Engineering Escola Politécnica da Universidade São Paulo Brazil

ISBN: (纸本)9780956426338

The growth of digital content generation and its access by the general public have, for the past few years, promoted the importance of resources' metadata, and enhanced the debate on their generation and quality. The improvement of new technologies and users needs have led to new metadata generation practices, which include the author-generated metadata. By studying the current literature on the subject we analyzed the author-generated metadata quality used on a given IPTV service. From the results of this study we propose an alternative methodology for insertion of metadata by the service user, where an auto-complete engine is applied aiming to enhance the system's metadata quality. © 2010 i-Society.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Cuckoo-based malware dynamic analysis

引用

International Journal of Performability engineering 2019年第3期15卷 772-781页

作者： Wang, Lele Wang, Binqiang Liu, Jiangang Miao, Qiguang Zhang, Jianhui National Digital Switching System Engineering and Technological Research Center Zhengzhou450002 China Nanjing Information Technology Institute Nanjing210000 China Department of Computer Science Xidian University Xi'an710071 China

Aiming at the problems of the huge number of malware currently in the big data environment, the insufficient ability of automatic malware analysis available, and the inefficiency of the classification of malicious attributes, in this paper, we propose a Cuckoo-based malware dynamic analysis system that can be extended, analyzed quickly, and has application value. The system proposes a semantic feature model based on deep learning, uses a deep recursive neural network model to describe the multi-layered aggregation relationship of program semantics, and builds a malware semantic aggregation model. The model can automatically complete the acquisition and analysis of behavioural features of unknown program samples and perform attribute discrimination on unknown program samples efficiently and accurately. © 2019 Totem Publisher, Inc.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cloud-based ecosystem proposal for applying an intelligent virtual assistant in online education 2

Cloud-based ecosystem proposal for applying an intelligent v...

引用

2nd Sustainable Cities Latin America Conference, SCLA 2021

作者： De Armas De Armas, Claudia Lopez, Fernando L. Gutierrez Kofuji, Sergio Takeo Bressan, Graca Tori, Romero Universidade de Sao Paulo Department of Electronic System Engineering Sao Paulo Brazil Universidade de Sao Paulo Department of Computer Engineering and Digital Systems Sao Paulo Brazil

ISBN: (纸本)9781665437684

Intelligent Virtual Assistants (IVA) or advanced chatbots are bringing many benefits in services. Achieving the robot-man interaction in an effective and affective way is not an easy task. However, it is possible to arrive at a model with the existing technological advances to create this expected interaction. In education, specifically in online learning, there are problems with student retention and learning effectiveness. Considering the problems presented, it is possible to use the great potential of IV As to support students and teachers during these courses and avoid some usual challenges. There are some platforms and services in the cloud with tools ready for the development of these IV As. Hence, this article aims to design a modular ecosystem for an IVA applied in education. Also, do a comparative study on platforms and services in the cloud: Amazon Web Service, Google, and Microsoft. The objective is to select the most complete and feasible according to our needs: Developing and hosting an IVA that allows interaction via text and user voice. As a result, the Microsoft service was selected. With the proposal of infrastructures, technologies, artificial intelligence elements, and technical direction was developed a modular ecosystem. © 2021 IEEE.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Multivariate Prediction of Building Energy Performance of Residential Buildings

引用

computers, Materials & Continua 2023年第6期75卷 5947-5964页

作者： Ibrahim Aliyu Tai-Won Um Sang-Joon Lee Chang Gyoon Lim Jinsul Kim Department of ICT Convergence System Engineering Chonnam National UniversityGwangju61186Korea Graduate School of Data Science Chonnam National UniversityGwangju61186Korea Interdisciplinary Program of Digital Future Convergence Service Chonnam National UniversityGwangju61186Korea Department of Computer Engineering Chonnam National UniversityYeosu59626Korea

In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest ***,effective design and planning for estimating heating load(HL)and cooling load(CL)for energy saving have become *** this vein,efforts have been made to predict the HL and CL using a univariate ***,this approach necessitates two models for learning HL and CL,requiring more computational ***,the one-dimensional(1D)convolutional neural network(CNN)has gained popularity due to its nominal computa-tional complexity,high performance,and low-cost hardware *** this paper,we formulate the prediction as a multivariate regression problem in which the HL and CL are simultaneously predicted using the 1D *** the building shape characteristics,one kernel size is adopted to create the receptive fields of the 1D CNN to extract the feature maps,a dense layer to interpret the maps,and an output layer with two neurons to predict the two real-valued responses,HL and *** the 1D data are not affected by excessive parameters,the pooling layer is not applied in this ***,the use of pooling has been questioned by recent *** performance of the proposed model displays a comparative advantage over existing models in terms of the mean squared error(MSE).Thus,the proposed model is effective for EPB prediction because it reduces computational time and significantly lowers the MSE.

关键词： Artificial intelligence(AI) convolutional neural network(CNN) cooling load deep learning energy energy load energy building performance heating load prediction

来源：评论

学校读者我要写书评

暂无评论

Design and optimization on dynamic power system for self-powered integrated wireless sensing nodes

Design and optimization on dynamic power system for self-pow...

引用

2005 International Symposium on Low Power Electronics and Design

作者： Ma, Dongsheng Wang, Janet M. Somasundaram, Mohankumar N. Hu, Zongqi Integrated System Design Laboratory Electrical and Computer Engineering Department University of Arizona Tucson AZ 85721 United States Digital VLSI Design Laboratory Electrical and Computer Engineering Department University of Arizona Tucson AZ 85721 United States

This paper presents an integrated power system for low-power wireless sensor networks with dynamic efficiency optimization technique. By adaptively resizing power transistors and adjusting switching frequency, system efficiency is enhanced significantly. Theoretical analysis is elaborated to support the proposed technique. A prototype integrated power system for self-powered photovoltaic wireless sensing node was designed and simulated with TSMC 0.35μm CMOS process. With a power range of 0.5μW to 10mW, power efficiency stays above 71%. Tolerance between theoretical and simulated optimal power transistor sizes is less than 6.7%, while that of optimal switching frequencies is less than 5%. The paper gives another solution to minimizing system power in the perspective of power processing. Copyright 2005 ACM.

关键词： Power electronics

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：