检索结果-内蒙古大学图书馆

Large scale air pollution prediction with deep convolutional networks

science China(Information sciences) 2021年第9期64卷 116-126页

作者： Gao HUANG Chunjiang GE Tianyu XIONG Shiji SONG Le YANG Baoxian LIU Wenjun YIN Cheng WU Department of Automation Tsinghua University Department of Computer Science University of Toronto School of Environment Tsinghua University Beijing Key Laboratory of Airborne Particulate Matter Monitoring Technology Beijing Municipal Environmental Monitoring Center Insights Value Technology CO. LTD.

Although considerable success has been achieved in urban air quality prediction(AQP) with machine learning techniques, accurate and long-term prediction is still challenging. One of the key issues for existing AQP approaches is that air quality monitoring stations are sparsely distributed, typically with around ten monitoring stations per city. As air quality may change abruptly in a local area, it is difficult to perform AQP accurately in areas that are far away from observation points. In addition, due to the large distance between every two monitoring stations, we cannot effectively leverage spatial relations among them to improve the AQP accuracy. In this paper, thanks to the development of low-cost air quality sensors, we are now able to collect a large-scale air quality dataset with 393 deployed air quality monitoring stations in a 120 km × 70 km region, which is more than ten times denser than existing AQP datasets. Further,we present a novel method to handle the data effectively. Specifically, we first convert the observed data from irregularly distributed monitoring stations into a regular image-like pollution map, which can then be processed with advanced deep convolutional networks. The experimental results show that the proposed approach can simultaneously model the temporal and spatial relations in our large-scale densely-observed dataset, leading to significantly improved AQP results.

关键词： air pollution prediction artificial intelligence convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Unmanned helicopter engine health management based on improved KPCA-LSTM intelligent algorithm

Unmanned helicopter engine health management based on improv...

引用

Machine Learning and Intelligent Systems Engineering (MLISE), International Conference on

作者： Zhang Tong Jiaming Wang Kangfa Xu Aviation Key Laboratory of Science and Technology on Airborne and Missle-borne Computer AVIC Xi'an Aeronautics Computing Technique Research Institute Xi'an China

ISBN: (数字)9798350375077

ISBN: (纸本)9798350375084

In order to solve the problems of difficulty in modeling the operating state of UAV engines, high computational complexity, and poor predictability, this paper improves the traditional data dimensionality reduction and health prediction methods, introduces a neural network model to solve the key parameters, and forms a Improve the KPCA-LSTM intelligent algorithm to manage the health of unmanned helicopter engines. This algorithm reduces the dimensionality of the engine input parameter data by improving the KPCA algorithm, reducing the input data dimension during subsequent modeling. It uses the LSTM algorithm to learn and reason about the dependence between healthy engine loading and input data, and achieves long-term operation of the UAV engine. Trends and predictions of remaining life. Simulation experiments show that the improved intelligent algorithm can effectively predict the remaining life of the engine.

关键词： Computational modeling Helicopters Neural networks Memory management Predictive models Prediction algorithms Autonomous aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

Design of airborne Bus Communication Platform based on Isomorphic Dual Redundancy Channels

Design of Airborne Bus Communication Platform based on Isomo...

引用

2023 7th International Conference on Electrical, Mechanical and computer Engineering (ICEMCE)

作者： Xiaohang Wang Kangfa Xu Yaxing Xu Aviation Key Laboratory of Science and Technology on Airborne and Missle-borne Computer Xi'an Aeronautics Computing Technique Research Institute AVIC Xi'an China

In order to solve the problem of low reliability of airborne bus communication platforms under limited volume, weight, power consumption, and computing power in airborne environments, the design scheme of the airborne bus communication platform was completed by demonstrating the software and hardware architecture of isomorphic dual redundancy channels. This design scheme first analyzes the usage scenarios and requirements indicators of the airborne bus communication platform, standardizes the design process based on the analysis indicators, and then designs a hardware architecture based on isomorphic dual redundancy channels according to the requirements and application environment of the design scheme. Finally, it focuses on the data interaction characteristics between the airborne product and the upper computer, Complete the design of dual redundancy data intelligent control software from the perspective of dual channel data flow and channel fault switching. Simulation examples show that this solution effectively solves the problems of high fault reporting rate and excessive resource redundancy in traditional equipment, and significantly improves the reliability of massive data transmission and reception in airborne environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of airborne Intelligent Computing System Oriented to Intelligent Task Processing 26

Design of Airborne Intelligent Computing System Oriented to ...

引用

26th ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Winter 2023

作者： Bai, Linting Wen, Pengcheng Xie, Jianchun Li, Yunxi Lin, Rongchao School of Computer Science Northwestern Polytechnical University Xi'an Aeronautics Computing Technique Research Institute Avic Xi'an China Xi'an Aeronautics Computing Technique Research Institute Avic Aviation Key Laboratory of Science and Technology on Airborne and Missile-borne Computer Xi'an China Xi'an Aeronautics Computing Technique Research Institute Avic Aeronautics Data and Sensor Business Unit Avic Xi'an China

ISBN: (纸本)9798350345865

The rapid development of artificial intelligence technology promotes the gradual evolution of the 'three integration' of mechanization, informatization and intelligence. The mass data characteristics of airborne mission informatization put forward higher demands on the storage, transmission and management capabilities of airborne data. The characteristics of high complexity, strong confrontation, strong real-time, and uncertainty of airborne intelligent tasks pose more challenges to the intelligent processing of airborne data. This paper analyzes the data characteristics and mission characteristics in the process of airborne intelligence missions, and proposes an airborne intelligent computing architecture for airborne data processing of intelligent missions. The composition and function of each technical layer are expounded, and several problems of airborne intelligent computing technology are analyzed. Finally, the development trend of airborne intelligent technology development is prospected. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Real Time Image Haze Removal on Multi-core DSP

引用

Procedia Engineering 2015年 99卷 244-252页

作者： Linting Bai Yongwei Wu Jianchun Xie Pengcheng Wen Department of Computer Science and Technology Tsinghua National Laboratory for Information Science and Technology(TNLIST) Tsinghua University Beijing 100084 China Technology Innovation Center at Yinzhou Yangtze Delta Region Institute of Tsinghua University 315100 ZheJiang AVIC Computing Technique Research Institute No.15 Jinye 2 steet Yanta District Xi’an 710065 China Aviation Key Laboratory of Science and Technology on Airborne and Missleborne Conputer No.15 Jinye2 street Yanta District Xi’an 710065 China

The quality and visual effect of an image is high demanded in avionic embedded field. But the frog and haze is common in the nature environment, so foggy images gathered in bad weather need to be disposed to remove the haze. The single image haze removal algorithm using dark channel prior can achieve great haze removal effect, but the process of optimizing the medium transmission in this algorithm costs too much time, while the computational complexity is too high to be real-time operating for high resolution image. In this paper, a novel method is proposed which uses a new kind of filter called guided filter to optimize the medium transmission. This method is much faster and also can achieve good haze removal effect. In addition, the method uses down sampling and interpolation method to transform a high resolution image into a low one to reduce the quantity of calculation. At last, we implement the novel algorithm on a multi-core DSP of TI company. The experimental results show that the method costs less than 40ms for a 600*400 resolution image and can satisfy the demand of real-time image process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Realization of Intelligent airborne Information Processing Concept Simulation System

Design and Realization of Intelligent Airborne Information P...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Jianchun Xie Linting Bai Qing Luo Aviation Key Laboratory of Science And Technology On Airborne And Missile-borne Computer AVIC Xi'an Aeronautics Computing Technique Research Institute Xi'an China College of Aerospace Engineering Nanjing University of Aeronautics and Astronautics Nanning China Shenyang Aircraft Design&Reserch Institute Shenyang China

Facing the development trend of future distributed cloud operations, intelligent operations, and the technical requirements of multi-machine collaborative operations in the aviation field, this paper further studies the unified data transmission and management of multiple platforms based on the research of the unified cloud intelligent combat system architecture. Distributed data storage and management, multi-platform open information processing resource management and other key technologies, on the basis of the principle prototype designed and implemented by ourselves, a set of conceptual simulation platforms have been constructed for the simulation and technical verification of the entire airborne information processing system.

关键词： Technical requirements Atmospheric modeling Systems architecture Collaboration Prototypes Information processing Market research

来源：评论

学校读者我要写书评

暂无评论

Design of airborne Intelligent Computing System Oriented to Intelligent Task Processing

Design of Airborne Intelligent Computing System Oriented to ...

引用

Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Winter), ACIS International Winter Conference on

作者： Linting Bai Pengcheng Wen Jianchun Xie Yunxi Li Rongchao Lin School of Computer Science Northwestern Polytechnical University Xi'an Aeronautics Computing Technique Research Institute AVIC Xi'an China Aviation Key Laboratory of Science and Technology on Airborne and Missile-borne Computer Xi'an Aeronautics Computing Technique Research Institute AVIC Xi'an China Xi'an Aeronautics Computing Technique Research Institute AVIC Aeronautics Data and Sensor Business Unit AVIC Xi'an China

The rapid development of artificial intelligence technology promotes the gradual evolution of the “three integration” of mechanization, informatization and intelligence. The mass data characteristics of airborne mission informatization put forward higher demands on the storage, transmission and management capabilities of airborne data. The characteristics of high complexity, strong confrontation, strong real-time, and uncertainty of airborne intelligent tasks pose more challenges to the intelligent processing of airborne data. This paper analyzes the data characteristics and mission characteristics in the process of airborne intelligence missions, and proposes an airborne intelligent computing architecture for airborne data processing of intelligent missions. The composition and function of each technical layer are expounded, and several problems of airborne intelligent computing technology are analyzed. Finally, the development trend of airborne intelligent technology development is prospected.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Author Correction: The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data

引用

Scientific data 2021年第1期8卷 72页

作者： Gilberto Pastorello Carlo Trotta Eleonora Canfora Housen Chu Danielle Christianson You-Wei Cheah Cristina Poindexter Jiquan Chen Abdelrahman Elbashandy Marty Humphrey Peter Isaac Diego Polidori Markus Reichstein Alessio Ribeca Catharine van Ingen Nicolas Vuichard Leiming Zhang Brian Amiro Christof Ammann M Altaf Arain Jonas Ardö Timothy Arkebauer Stefan K Arndt Nicola Arriga Marc Aubinet Mika Aurela Dennis Baldocchi Alan Barr Eric Beamesderfer Luca Belelli Marchesini Onil Bergeron Jason Beringer Christian Bernhofer Daniel Berveiller Dave Billesbach Thomas Andrew Black Peter D Blanken Gil Bohrer Julia Boike Paul V Bolstad Damien Bonal Jean-Marc Bonnefond David R Bowling Rosvel Bracho Jason Brodeur Christian Brümmer Nina Buchmann Benoit Burban Sean P Burns Pauline Buysse Peter Cale Mauro Cavagna Pierre Cellier Shiping Chen Isaac Chini Torben R Christensen James Cleverly Alessio Collalti Claudia Consalvo Bruce D Cook David Cook Carole Coursolle Edoardo Cremonese Peter S Curtis Ettore D'Andrea Humberto da Rocha Xiaoqin Dai Kenneth J Davis Bruno De Cinti Agnes de Grandcourt Anne De Ligne Raimundo C De Oliveira Nicolas Delpierre Ankur R Desai Carlos Marcelo Di Bella Paul di Tommasi Han Dolman Francisco Domingo Gang Dong Sabina Dore Pierpaolo Duce Eric Dufrêne Allison Dunn Jiří Dušek Derek Eamus Uwe Eichelmann Hatim Abdalla M ElKhidir Werner Eugster Cacilia M Ewenz Brent Ewers Daniela Famulari Silvano Fares Iris Feigenwinter Andrew Feitz Rasmus Fensholt Gianluca Filippa Marc Fischer John Frank Marta Galvagno Mana Gharun Damiano Gianelle Bert Gielen Beniamino Gioli Anatoly Gitelson Ignacio Goded Mathias Goeckede Allen H Goldstein Christopher M Gough Michael L Goulden Alexander Graf Anne Griebel Carsten Gruening Thomas Grünwald Albin Hammerle Shijie Han Xingguo Han Birger Ulf Hansen Chad Hanson Juha Hatakka Yongtao He Markus Hehn Bernard Heinesch Nina Hinko-Najera Lukas Hörtnagl Lindsay Hutley Andreas Ibrom Hiroki Ikawa Marcin Jackowicz-Korczynski Dalibor Janouš Wilma Jans Rachhpal Jassal Shicheng Jiang Tomomichi Kato Myr Computational Research Division Lawrence Berkeley National Laboratory Berkeley CA 94720 USA. gzpastorello@lbl.gov. DIBAF University of Tuscia Viterbo 01100 Italy. Euro-Mediterranean Centre on Climate Change Foundation (CMCC) Lecce 73100 Italy. Climate & Ecosystem Sciences Division Lawrence Berkeley National Laboratory Berkeley CA 94720 USA. Computational Research Division Lawrence Berkeley National Laboratory Berkeley CA 94720 USA. Department of Civil Engineering California State University Sacramento CA 95819 USA. Department of Geography Environment and Spatial Sciences Michigan State University East Lansing MI 48823 USA. Department of Computer Science University of Virginia Charlottesville VA 22904 USA. TERN Ecosystem Processes Menzies Creek VIC3159 Australia. Max Planck Institute for Biogeochemistry Jena 07701 Germany. Laboratoire des Sciences du Climat et de l'Environnement (LSCE) CEA CNRS UVSQ UPSACLAY Gif sur Yvette 91190 France. Key Laboratory of Ecosystem Network Observation and Modeling Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing 100101 China. Department of Soil Science University of Manitoba Winnipeg MB R3T2N2 Canada. Department of Agroecology and Environment Agroscope Research Institute Zürich 8046 Switzerland. School of Geography and Earth Sciences McMaster University L8S4K1 Hamilton ON Canada. Department of Physical Geography and Ecosystem Science Lund University Lund 22362 Sweden. Department of Agronomy and Horticulture University of Nebraska-Lincoln Lincoln NE 68583 USA. School of Ecosystem and Forest Sciences The University of Melbourne Richmond VIC3121 Australia. Department of Biology Research Group PLECO University of Antwerp Antwerp 2610 Belgium. Joint Research Centre European Commission Ispra 21027 Italy. TERRA Teaching and Research Center University of Liege Gembloux B-5030 Belgium. Finnish Meteorological Institute Helsinki 00560 Finland. ES

A Correction to this paper has been published: https://***/10.1038/s41597-021-00851-9.

关键词：

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：