检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

410 篇 会议
7 篇 期刊文献

馆藏范围

417 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

274 篇 工学
- 220 篇 计算机科学与技术...
- 138 篇 软件工程
- 49 篇 航空宇航科学与技...
- 44 篇 电子科学与技术（可...
- 44 篇 信息与通信工程
- 31 篇 电气工程
- 28 篇 控制科学与工程
- 22 篇 仪器科学与技术
- 19 篇 机械工程
- 12 篇 光学工程
- 12 篇 土木工程
- 12 篇 生物工程
- 9 篇 生物医学工程（可授...
- 9 篇 安全科学与工程
- 8 篇 测绘科学与技术
- 8 篇 网络空间安全
- 7 篇 建筑学
- 6 篇 化学工程与技术
- 6 篇 交通运输工程
88 篇 理学
- 36 篇 物理学
- 20 篇 数学
- 16 篇 地球物理学
- 15 篇 生物学
- 8 篇 化学
- 8 篇 天文学
- 7 篇 大气科学
34 篇 管理学
- 23 篇 管理科学与工程(可...
- 16 篇 图书情报与档案管...
- 14 篇 工商管理
8 篇 医学
- 7 篇 临床医学
5 篇 经济学
4 篇 法学
2 篇 农学
2 篇 军事学
1 篇 教育学
1 篇 文学

主题

61 篇 data handling
10 篇 field programmab...
9 篇 space applicatio...
7 篇 system-on-chip
7 篇 machine learning
5 篇 deep learning
5 篇 edge computing
4 篇 data processing
4 篇 big data
4 篇 cosmology
4 篇 euclid
4 篇 artificial intel...
3 篇 reinforcement le...
3 篇 spacecraft
3 篇 signal processin...
3 篇 synthetic apertu...
3 篇 nisp
3 篇 soil moisture
2 篇 imaging
2 篇 instruments

机构

20 篇 european space a...
9 篇 airbus defence a...
9 篇 thales alenia sp...
7 篇 european space a...
7 篇 european space r...
6 篇 noordwijk
6 篇 ramon.space ltd....
6 篇 dsi aerospace gm...
6 篇 hamburg universi...
6 篇 airbus defence a...
4 篇 beyond gravity a...
4 篇 airbus defence a...
4 篇 department of in...
4 篇 technical univer...
4 篇 european space r...
4 篇 caltech jet prop...
4 篇 thales alenia sp...
4 篇 esa noordwijk
4 篇 university of pi...
3 篇 thales alenia sp...

作者

8 篇 david steenari
7 篇 steenari david
7 篇 fanucci luca
6 篇 siegle felix
6 篇 felix siegle
6 篇 kostas marinis
6 篇 marinis kostas
6 篇 laurent hili
6 篇 luca fanucci
6 篇 hili laurent
5 篇 olivier mourra
5 篇 moranti silvia
5 篇 nannipieri pietr...
5 篇 mourra olivier
5 篇 silvia moranti
4 篇 schirmer m.
4 篇 dario pascucci
4 篇 pietro nannipier...
4 篇 pascucci dario
4 篇 sirignano c.

语言

414 篇 英文
3 篇 其他

检索条件"任意字段=2023 European Data Handling and Data Processing Conference for Space, EDHPC 2023"

共 417 条记录，以下是351-360 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Integrating Ideal Characteristics of Chat-GPT Mechanisms into the Metaverse: Knowledge, Transparency, and Ethics 1

引用

3rd International Multi-Disciplinary conference - Theme: Integrated Sciences and Technologies, IMDC-IST 2024

作者： Atiyah, Abbas Gatea Faris, NimetAllah Nasser Rexhepi, Gadaf Qasim, Alaa Jabbar Faculty of Administration and Economic University of Thi-Qar Nasiriyah Iraq College of Arts Department of English University of Basrah Basrah Iraq Southeast European University Tetovo Macedonia School of Computing College of Arts and Sciences Universiti Utara Malaysia Kedah Sintok06010 Malaysia

ISBN: (数字)9783031517167

ISBN: (纸本)9783031517150

Chat-GPT is a very advanced language model in artificial intelligence. It can be used in administrative and economic research and has many other applications. On the other hand, the metaverse is a wide and expansive space that expresses a virtual reality about the nature of the service or product that was recently produced or developed. It is possible to integrate these two tools by introducing the ideal mechanisms of Chat-GPT into metaverse applications. This study deals with a logical presentation to form a research framework on the process of integrating Chat-GPT mechanisms into metaverse applications. By referring to the literature related to Chat-GPT, it is argued that these three mechanisms (knowledge development, transparency of the artificial intelligence system, and ethical implications) have an important role in changing the speed and efficiency of processing big data to generate very accurate information. Therefore, the light was shed on the abovementioned mechanisms. as they provide a great insight into complex events by revealing hidden patterns and insightful information within data, facilitating improved data capture. The conclusion of the study led to the central role played by the ideal mechanisms of Chat-GPT in building a broad and reliable structure of information about various events and tasks, regardless of their complexity. Therefore, there is a good possibility to form a future research framework that about the role of ideal mechanisms of Chat-GPT in the metaverse applications. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Euclid: The Near Infrared Spectrometer and Photometer (NISP) Instrument Operations

Euclid: The Near Infrared Spectrometer and Photometer (NISP)...

引用

conference on space Telescopes and Instrumentation - Optical, Infrared, and Millimeter Wave

作者： Battaglia, P. Sirignano, C. Dusini, S. Gregorio, A. Ligori, S. Medinaceli, E. Romelli, E. Zacchei, A. Barbier, R. Gillard, W. Copin, Y. Jahnke, K. Schirmer, M. Auricchio, N. Balbi, E. Balestra, A. Bonino, D. Borsato, E. Brescia, M. Capobianco, V Cavuoti, S. Cogato, F. Conseil, S. Corcione, L. Davini, S. Delucchi, G. Farinelli, R. Franceschi, E. Grupp, F. Kubik, B. Lentini, E. Lhoussaine, R. Maciaszek, T. Morgante, G. Passalacqua, F. Polenta, G. Riccio, G. Scodeggio, M. Testera, G. Tosi, S. Trifoglio, M. Troja, A. Valenziano, L. Osservatorio Astrofis & Sci Spazio INAF OAS Via Gobetti 93-3 I-40129 Bologna Italy Univ Padua Dipartimento Fis & Astron G Galilei Via Marzolo 8 I-35131 Padua Italy Ist Nazl Fis Nucl Sez Padova Via F Marzolo 8 Padua Italy Univ Trieste Dipartimento Fis Via A Valerio 2 I-34127 Trieste Italy INAF Osservatorio Astron Trieste Via GB Tiepolo 11 I-34143 Trieste Italy INAF OATo Via Osservatorio 20 I-10025 Turin Italy Univ Claude Bernard Lyon 1 CNRS IN2P3 IP21 Lyon UMR 5822 F-69100 Villeurbanne France Aix Marseille Univ CNRS IN2P3 CPPM Marseille France Max Planck Inst Astron Konigstuhl 17 D-69117 Heidelberg Germany Ist Nazl Fis Nucl Sez Genova Via Dodecaneso 33 I-16146 Genoa Italy INAF Osservatorio Astron Padova Vicolo Osservatorio 5 I-35122 Padua Italy INAF OACN Salita Moiariello 16 I-80131 Naples Italy Univ Napoli Federico II Dept Phys E Pancini Naples Italy Ludwig Maximilians Univ Munchen Univ Sternwarte Munchen Fak Phys Scheinerstr 1 D-81679 Munich Germany Ctr Natl Etud Spatiales Toulouse France Agenzia Spaziale Italiana Via Politecn I-00133 Rome Italy INAF IASF Milano Via Alfonso Corti 12 I-20133 Milan Italy

ISBN: (纸本)9781510675087;9781510675070

Euclid is a european space Agency (ESA) wide-field space mission dedicated to the high-precision study of dark energy and dark matter. In July 2023 a space X Falcon 9 launch vehicle put the spacecraft in its target orbit, located 1.5 million kilometers away from Earth, for a nominal lifetime of 6.5 years. The survey will be realized through a wide field telescope and two instruments: a visible imager (VIS) and a Near Infrared Spectrometer and Photometer (NISP). NISP is a state-of-the-art instrument composed of many subsystems, including an optomechanical assembly, cryogenic mechanisms, and active thermal control. The Instrument Control Unit (ICU) is interfaced with the spaceCraft and manages the commanding and housekeeping production while the high-performance data processing Unit manages more than 200 Gbit of compressed data acquired daily during the nominal survey. To achieve the demanding performance necessary to meet the mission's scientific goals, NISP requires periodic in-flight calibrations, instrument parameters monitoring, and careful control of systematic effects. The high stability required implies that operations are coordinated and synchronized with high precision between the two instruments and the platform. Careful planning of commanding sequences, look-ahead, and forecasting instrument monitoring is needed, with greater complexity than previous survey missions. Furthermore, NISP is operated in different environments and configurations during development, verification, commissioning, and nominal operations. This paper presents an overview of the NISP instrument operations at the beginning of routine observations. The necessary tools, workflows, and organizational structures are described. Finally, we show examples of how instrument monitoring was implemented in flight during the crucial commissioning phase, the effect of intense Solar activity on the transmission of onboard data, and how IOT successfully addressed this issue.

关键词： Instrument Operations space Instrument Euclid NISP Cosmology survey slitless spectroscopy photometry

来源：评论

学校读者我要写书评

暂无评论

Feasibility Study to Detect Floating Debris by Hyperspectral Mission Using Onboard AI

Feasibility Study to Detect Floating Debris by Hyperspectral...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Nafiseh Ghasemi Jens Nieke Marco Celesti Gianluigi Di Cosimo Roberto Camarero Ferran Gascon Nicolas Longepe Raffaele Vitulli Marco Rovatti European Space Agency European Space Research and Technology Centre (ESA-ESTEC) AZ Noordwijk The Netherlands

The Copernicus Hyperspectral Imaging Mission for the Environment (CHIME) will provide routine hyperspectral observations over the land and coastal zone through the Copernicus Program in support of EU- and related policies for the management of natural resources, assets and benefits [1] , [2] . CHIME is an operational mission covering land and coastal areas which already uses of well-established ground processing routines in place that is independent of the AI unit we are discussing here. Areas outside the nominal observation scenario call for new methodologies such as on-board processing which will bring advantages including: fast processing of data, reducing the amount of data to be down-linked especially over ocean that CHIME sensor will be on but there is no regular acquiring plan, capability of on demand request handling. However there are some drawbacks i.e. complex validation and setting up update routines. Therefore, there has been an assessment going on to have an artificial intelligence unit on board to process acquired data and select only part of the data that contains desired targets. Based on the importance of detecting floating plastic debris for applications such as fishing farms preservation, navigation, tourism, etc., in marine environment, this application has been selected to serve as one of the test cases to evaluate Artificial Intelligence (AI) on board [3] .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impact Assessment of the Catastrophic Earthquakes of February 2023 in Turkey and Syria via the exploitation of satellite datasets 9

Impact Assessment of the Catastrophic Earthquakes of Februar...

引用

9th International conference on Remote Sensing and Geoinformation of the Environment, RSCy 2023

作者： Fotiou, Kyriaki Argyriou, Athanasios V. Alatza, Stavroula Theocharidis, Christos Loupasakis, Constantinos Prodromou, Maria Apostolakis, Alexis Pittaki-Chrysodonta, Zambella Kaskara, Mariza Kontoes, Charalampos Themistocleous, Kyriacos Hadjimitsis, Diofantos G. Tzouvaras, Marios ERATOSTHENES Centre of Excellence Department of Resilient Society 82 Franklin Roosevelt Limassol3012 Cyprus Cyprus University of Technology Department of Civil Engineering and Geomatics P.O BOX 50329 Limassol3036 Cyprus National Observatory of Athens Operational Unit BEYOND Centre for Earth Observation Research and Satellite Remote Sensing IAASARS/NOA AthensGR-152 36 Greece Laboratory of Engineering Geology and Hydrogeology School of Mining and Metallurgical Engineering National Technical University of Athens Zografou Campus Athens15780 Greece

ISBN: (纸本)9781510668225

Turkey due to its location within the collision zone between the Eurasian, African and Arabian Plates, is a region prone to earthquakes. The country mostly lies on the Anatolian micro-plate, bounded by two major strike-slip fault zones, i.e., the North and the East Anatolian Fault. On 6 February 2023, the activation of a large segment of the East Anatolian Fault generated two earthquakes of 7.8 and 7.5 magnitude, in southern Turkey. The seismic risk is greater along the plate boundaries, however due to the frequency of earthquake occurrence throughout Turkey, detailed seismic risk maps are crucial and need to be continuously updated towards operational purposes, and as the optimal means towards decision making for disaster risk reduction. Extensive Synthetic Aperture Radar (SAR) satellite image analysis was performed to determine ground displacements caused by the seismic sequence in the wider area around the two epicenters. Pre-seismic line of sight displacements, as well as co-seismic deformation, were estimated, providing critical information about the surface rupture and the overall ground deformation in the affected areas. Earthquakes can induce landslides and other ground displacements causing extensive damage to buildings and infrastructure. Therefore, optical (e.g., Sentinel-2, PlanetScope) and SAR (Sentinel-1) imagery were exploited as a useful tool for assessing the impact of earthquakes on the ground. The monitoring and mapping of these changes, in conjunction with SAR analysis, as well as information on building infrastructure and population density, highlight the overall damage assessment in the region, thus, allowing a better understanding of the impact of earthquakes while providing a more effective response and recovery efforts for decision makers and local authorities towards disaster risk reduction. © 2023 SPIE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds 37

Tackling Heavy-Tailed Rewards in Reinforcement Learning with...

引用

37th conference on Neural Information processing Systems (NeurIPS)

作者： Huang, Jiayi Zhong, Han Wang, Liwei Yang, Lin F. Peking Univ Ctr Data Sci Beijing Peoples R China Peking Univ Natl Key Lab Gen Artificial Intelligence Sch Intelligence Sci & Technol Beijing Peoples R China Univ Calif Los Angeles Los Angeles CA USA

ISBN: (纸本)9781713899921

While numerous works have focused on devising efficient algorithms for reinforcement learning (RL) with uniformly bounded rewards, it remains an open question whether sample or time-efficient algorithms for RL with large state-action space exist when the rewards are heavy-tailed, i.e., with only finite (1 +epsilon)-th moments for some epsilon is an element of (0, 1]. In this work, we address the challenge of such rewards in RL with linear function approximation. We first design an algorithm, HEAVY-OFUL, for heavy-tailed linear bandits, achieving an instance-dependent T-round regret of (O) over tilde (dT1-epsilon/2(1+epsilon) root Sigma(T)(t=1)nu(2)(t) + dT1-epsilon/2(1+epsilon), the first of this kind. Here, d is the feature dimension, and nu(1+epsilon)(t) is the (1 +epsilon)-th central moment of the reward at the t-th round. We further show the above bound is minimax optimal when applied to the worst-case instances in stochastic and deterministic linear bandits. We then extend this algorithm to the RL settings with linear function approximation. Our algorithm, termed as HEAVY-LSVI-UCB, achieves the first computationally efficient instance-dependent K-episode regret of (O) over tilde (d root HU*K1/1+epsilon + d root HV* K). Here, H is length of the episode, and U*, V* are instance-dependent quantities scaling with the central moment of reward and value functions, respectively. We also provide a matching minimax lower bound Omega(dHK(11+epsilon) + d root(HK)-K-3) to demonstrate the optimality of our algorithm in the worst case. Our result is achieved via a novel robust self-normalized concentration inequality that may be of independent interest in handling heavy-tailed noise in general online regression problems.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Land Monitoring Service for Local Public Administrations: The IRIDE EOS4LPA Lot 3 Project 26th

A Land Monitoring Service for Local Public Administrations: ...

引用

26th Italian conference on Geomatics for Environmental Monitoring: From data to Services (ASITA)

作者： Aiello, Antonello Massimi, Vincenzo Taggio, Nicolo Borrelli, Raffaele Laurino, Vincenzo Filippi, Elisa Decaro, Paolo Lo Zito, Fabio D'Aranno, Peppe Marsella, Maria Quattrociocchi, Dino Brunetti, Alessandro Casucci, Marco Planetek Italia Srl Via Massaua 12 Bari Italy Sapienza Univ Rome Piazzale Moro 5 Rome Italy Spark Replay Srl Corso Francia 110 Turin Italy Serco Italia SpA Viale Tecn 161 Rome Italy Survey Lab Srl Via Eudossiana 18 Rome Italy eGEOS SPA Via Tiburtina 965 Rome Italy NHAZCA Srl Via Bachelet 12 Rome Italy EMSEE SPACE ESA IRIDE Integrated Project Team Rome Italy

ISBN: (纸本)9783031599248;9783031599255

By addressing the green and digital transition challenges within the Next Generation EU, the Italian PNRR identified an investment in a new "constellation of constellations" of Low Earth Orbit satellites called IRIDE. By the end of 2026, the IRIDE Programme will develop a satellite infrastructure for Earth Observation (EO) to provide services to the Public Administration. Within IRIDE, the EOS4LPA Lot 3 project foresees the development of "Cross-Monitoring of Ground Motion and Hot Spots of Land Cover Change" service for local public administrations (LPA), including regional authorities, municipalities and hydrographic districts. The service will be developed by Planetek Italia (Prime Contractor), together with Serco Italia, Spark Reply, Survey Lab, e-geos and NHAZCA, to provide the following EO-based products by integrating existing operational solutions: . the thematic grid ground motion (GGM) . the burnt area map and fire severity map layers (BAM&FSM) . the land cover change layer (LCC) . the building stability assessment at the municipality scale (I-MODI). All involved processing chains will be fed by available open satellite data (e.g., the Sentinels, Landsat, etc.) and monitoring services (e.g., EGMS and other Copernicus Core Services, data available within the LPAs repositories, etc.) until the forthcoming IRIDE data and services are ready. IRIDE EOS4LPA aims to generate and increase LPA's awareness of the benefits of EO-based services for monitoring the territory. It will demonstrate such solutions' effectiveness and reliability in supporting everyday operations and decision-making processes, attaining their needs and reaching the quality requirements-with a cost-effective approach.

关键词： PNRR EO IRIDE satellite service ground motion burnt area mapping fire severity mapping land cover change building stability local public administrations

来源：评论

学校读者我要写书评

暂无评论

Room Adaptation of Training data for Distant Speech Recognition

Room Adaptation of Training Data for Distant Speech Recognit...

引用

european Signal processing conference (EUSIPCO)

作者： James Fosburgh Dushyant Sharma Patrick A. Naylor Research & Development Nuance Communications Inc. USA Electrical & Electronic Engineering Imperial College London UK

We present a novel signal processing-based approach for estimating room impulse responses for augmentation of ASR training data that is best suited to the reverberation characteristics in a particular acoustic space. Our approach estimates an impulse response of a room by using a supervised adaptive system identification algorithm to extract the relative transfer function between a speech source played through a loudspeaker and recorded by a microphone. These impulse responses can then be applied to clean speech files to create an augmented training set for an ASR system. Given the availability of a small amount of this type of playback audio for a room, we show that an ASR model trained with our data augmentation approach can provide a 19% relative reduction in word error rate compared to a system using random augmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pruning and Early-Exit Co-Optimization for CNN Acceleration on FPGAs

Pruning and Early-Exit Co-Optimization for CNN Acceleration ...

引用

Design, Automation and Test in Europe conference and Exhibition (DATE)

作者： Korol, Guilherme Jordan, Michael Guilherme Rutzig, Mateus Beck Castrillon, Jeronimo Beck, Antonio Carlos Schneider Univ Fed Rio Grande do Sul UFRGS Inst Informat Porto Alegre Brazil Univ Fed Santa Maria UFSM Elect & Comp Dept Santa Maria Brazil Tech Univ Dresden Ctr Adv Elect Dresden Dresden Germany Ctr Scalable Data Analyt & Artificial Intelligenc Dresden Germany

ISBN: (纸本)9798350396249

The challenge of processing heavy-load ML tasks, particularly CNN-based ones at resource-constrained IoT devices, has encouraged the use of edge servers. The edge offers performance levels higher than the end devices and better latency and security levels than the Cloud. On top of that, the rising complexity of ML applications, the ever-increasing number of connected devices, and the current demands for energy efficiency require optimizing such CNN models. Pruning and early-exit are notable optimizations that have been successfully used to alleviate the computational cost of inference. However, these optimizations have not yet been exploited simultaneously: while pruning is usually applied at design time, which involves retraining the CNN before deployment, early-exit is inherently dynamic. In this work, we propose AdaPEx, a framework that exploits the intrinsic reconfigurable FPGA capabilities so both can be cooperatively employed. AdaPEx first explores the trade-off between pruning and early-exit at design-time, creating a design space never exploited in the state-of-the-art. Then, AdaPEx applies FPGA reconfiguration as a means to enable the combined use of pruning and early-exit dynamically. At runtime, this allows matching the inference processing to the current edge conditions and a user-configurable accuracy threshold. In a smart IoT application, AdaPEx processes up to 1.32x more inferences and improves EDP by up to 2.55x over the state-of-the-art FPGA-based FINN accelerator.

关键词： Edge Computing Adaptive Inference CNN FPGA

来源：评论

学校读者我要写书评

暂无评论

Enhancing Land Cover Maps with Optical Time Series and Ambiguous Loss Function 29

Enhancing Land Cover Maps with Optical Time Series and Ambig...

引用

conference on Image and Signal processing for Remote Sensing XXIX

作者： Francis, Alistair Marszalek, Michael Wheeler, James Senaras, Caglar Davis, Timothy Wania, Annett European Space Agcy Via Galileo Galilei 1 Frascati Italy Planet Labs Wilhelminastr 43A NL-2011VK Haarlem Netherlands Planet Labs GmbH Kurfurstendamm 22 D-10719 Berlin Germany

ISBN: (纸本)9781510666955;9781510666962

Land cover classification products such as the Corine Land Cover (CLC) project provide Europe-wide maps at a resolution that is relatively coarse in comparison to many remote sensing instruments. Features such as roads, individual buildings, small rivers, and many others are missed due to this. In this work, we present a method to increase the resolution of land cover maps using a combination of the existing CLC product, and high resolution optical time series. The RapidAI4EO corpus is an open-data collection of half a million time series over Europe, and includes a 3 m/pixel resolution Planet Fusion product, spanning two years (2018-2019). A standard supervised learning approach with this data, using the CLC labels as direct ground-truth over each pixel, would lead to many incorrect labels, because of the inexact delineation of classes at the comparatively lower resolution of the CLC map. With this in mind, we have developed a land cover classification model which is trained using a novel loss function-ambiguous cross-entropy-that takes into account the fuzzy nature of the CLC labels. The ambiguous cross-entropy loss allows the model to learn from imprecise labels. Models are trained for each of the three CLC class levels, and compared. Statistical metrics for agreement between CLC, the trained models, and a high-resolution land cover map derived from OpenStreetMap are measured in a set of validation sites across Europe. This work demonstrates how machine learning can enhance an existing product's resolution, without the need for time-consuming labeling at such a fine scale.

关键词： Land cover classification Planet Fusion Self-Supervised Learning Ambiguous Loss

来源：评论

学校读者我要写书评

暂无评论

Lessons Learned from Ariel data Challenge 2022 Inferring Physical Properties of Exoplanets From Next-Generation Telescopes 36

Lessons Learned from Ariel Data Challenge 2022 Inferring Phy...

引用

36th Annual conference on Neural Information processing Systems - Competition Track, NeurIPS 2022

作者： Yip, Kai Hou Changeat, Quentin Waldmann, Ingo Unlu, Eyup B. Forestano, Roy T. Roman, Alexander Matcheva, Katia Matchev, Konstantin T. Stefanov, Stefan Podsztavek, Ondřej Morvan, Mario Nikolaou, Nikolaos Al-Refaie, Ahmed Jenner, Clare Johnson, Chris Tsiaras, Angelos Edwards, Billy de Oliveira, Catarina Alves Thiyagalingam, Jeyan Lagage, Pierre-Olivier Cho, James Tinetti, Giovanna Department of Physics and Astronomy University College London Gower Street United Kingdom 3700 San Martin Drive BaltimoreMD21218 United States Physics Department University of Florida GainesvilleFL32611 United States Faculty of Information Technology Czech Technical University in Prague Thákurova 9 Prague 6160 00 Czech Republic EPCC The University of Edinburgh United Kingdom INAF - Osservatorio Astrofisico di Arcetri Florence Italy Leiden Netherlands European Space Agency ESAC Villanueva de la Cãnada MadridE-28692 Spain STFC Scientific Computing Rutherford Appleton Laboratory Science and Technology Facilities Council Harwell Campus OX11 0QX United Kingdom Centre Energie Atomique Saclay France Martin A. Fisher School of Physics Brandeis University 415 South Street WalthamMA02453 United States

Exo-atmospheric studies, i.e. the study of exoplanetary atmospheres, is an emerging frontier in Planetary Science. To understand the physical properties of hundreds of exoplanets, astronomers have traditionally relied on sampling-based methods. However, with the growing number of exoplanet detections (i.e. increased data quantity) and advancements in technology from telescopes such as JWST and Ariel (i.e. improved data quality), there is a need for more scalable data analysis techniques. The Ariel data Challenge 2022 aims to find interdisciplinary solutions from the NeurIPS community. Results from the challenge indicate that machine learning (ML) models have the potential to provide quick insights for thousands of planets and millions of atmospheric models. However, the machine learning models are not immune to data drifts, and future research should investigate ways to quantify and mitigate their negative impact. © 2023 K.H. Yip et al.

关键词： Physical properties

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共42页 << < 32 33 34 35 36 37 38 39 40 41 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：