检索结果-内蒙古大学图书馆

Improved retrieval for Challenging Scenarios in Clique-Based Neural Networks 13

13th International Work-Conference on Artificial Neural Networks (IWANN)

作者： Jiang, Xiaoran Marques, Max Raphael Sobroza Kirsch, Pierre-Julien Berrou, Claude UMR CNRS Labsticc Telecom Bretagne Dept Elect F-29238 Brest France

ISBN: (纸本)9783319192581;9783319192574

This paper describes new retrieval algorithms based on heuristic approach in clique-based neural networks introduced by Gripon and Berrou. This associative memory model resembles the well-known Willshaw model with specificity of clustered structure. Several retrieval algorithms exist, for instance, Winners-Take-All and Losers-Kicked-Out. These methods work generally well when the input message suffers reasonable distortions, but the performance drops dramatically in some challenging scenarios because of severe interference. By means of simulations, we show that the proposed heuristic retrieval algorithms are able to significantly mitigate this issue while maintaining biological plausibility to some extent.

关键词： Associative memory retrieval algorithms Sparse coding Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

How Many Parameters Can Be Maximally Estimated From a Set of Measurements?

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2015年第5期12卷 1081-1085页

作者： Konings, Alexandra G. McColl, Kaighin A. Piles, Maria Entekhabi, Dara MIT Dept Civil & Environm Engn Cambridge MA 02139 USA Univ Politecn Cataluna Dept Teoria Senyal & Comunicac Remote Sensing Lab ES-08034 Barcelona Spain SMOS Barcelona Expert Ctr Barcelona 08003 Spain

Remote sensing algorithms often invert multiple measurements simultaneously to retrieve a group of geophysical parameters. In order to create a robust retrieval algorithm, it is necessary to ensure that there are more unique measurements than parameters to be retrieved. If this is not the case, the inversion might have multiple solutions and be sensitive to noise. In this letter, we introduce a methodology to calculate the number of (possibly fractional) "degrees of information" in a set of measurements, representing the number of parameters that can be retrieved robustly from that set. Since different measurements may not be mutually independent, the amount of duplicate information is calculated using the information-theoretic concept of total correlation (a generalization of mutual information). The total correlation is sensitive to the full distribution of each measurement and therefore accounts for duplicate information even if multiple measurements are related only partially and nonlinearly. The method is illustrated using several examples, and applications to a variety of sensor types are discussed.

关键词： Algorithm design mutual information retrieval algorithms total correlation

来源：评论

学校读者我要写书评

暂无评论

ASSESSMENT AND DEVELOPMENT OF REMOTE SENSING BASED algorithms FOR WATER QUALITY MONITORING IN OLUSHANDJA DAM, NORTH-CENTRAL NAMIBIA

ASSESSMENT AND DEVELOPMENT OF REMOTE SENSING BASED ALGORITHM...

引用

作者： TAIMI SOFIA KAPALANGA University of Zimbabwe

学位级别：硕士

Olushandja Dam is amongst Namibia's inland water bodies that store and supply water to towns such as Outapi, Oshikuku and Oshakati. The dam is part of a complex water supply system that transports inter-basin water from the Kunene River Basin into Cuvelai Basin in the north-central regions of Namibia via a canal. There are potential sources of pollution along the route of the canal and around the dam which have effects on the water quality in the canal and eventually in the Olushandja Dam. Therefore, frequent and continuous monitoring of water quality is needed to allow timely decisions on the management of this critical resource. Specifically, the study sought to measure water quality at selected points in the dam and on the canal. This study used Landsat 8, 30 m resolution imagery to derive water quality parameters using retrieval algorithms. Water quality parameters included total suspended matter, turbidity, total nitrogen, nitrates, ammonia, total phosphorus and total algae counts. The study was carried out from November 2014 to June 2015. The retrieval algorithms were developed from a simple regression analysis between reflectance values of satellite images and field measurements. Statistical analyses were carried out to assess correlation between Landsat 8 predicted and field measured data. The field measurements showed that the dam and canal water is of low risk to human and is suitable for livestock watering. Turbidity levels exceeded the recommended limits set by NamWater is thus likely to cause complications in drinking water treatment as well as human and aquatic life. The study also found that all water quality parameter regression algorithms had high correlation coefficients (R 2 ) which was between 0.980-0.999. Therefore, the study concludes that the developed regression algorithms are best fit to predict water quality parameters from satellite data. Remote sensing is therefore recommended for frequent and continuous monitoring of Olushandja Dam as it

关键词： Olushandja Dam Landsat Remote Sensing retrieval algorithms Water Quality

来源：评论

学校读者我要写书评

暂无评论

Review of Machine Learning Approaches for Biomass and Soil Moisture retrievals from Remote Sensing Data

引用

REMOTE SENSING 2015年第12期7卷 16398-16421页

作者： Ali, Iftikhar Greifeneder, Felix Stamenkovic, Jelena Neumann, Maxim Notarnicola, Claudia Natl Univ Ireland Univ Coll Cork Dept Geog Cork Ireland TEAGASC Spatial Anal Unit Dublin Ireland EURAC Res Inst Appl Remote Sensing Bolzano Italy Ecole Polytech Fed Lausanne Signal Proc Lab CH-1015 Lausanne Switzerland CALTECH Jet Prop Lab Pasadena CA 91109 USA

The enormous increase of remote sensing data from airborne and space-borne platforms, as well as ground measurements has directed the attention of scientists towards new and efficient retrieval methodologies. Of particular importance is the consideration of the large extent and the high dimensionality (spectral, temporal and spatial) of remote sensing data. Moreover, the launch of the Sentinel satellite family will increase the availability of data, especially in the temporal domain, at no cost to the users. To analyze these data and to extract relevant features, such as essential climate variables (ECV), specific methodologies need to be exploited. Among these, greater attention is devoted to machine learning methods due to their flexibility and the capability to process large number of inputs and to handle non-linear problems. The main objective of this paper is to provide a review of research that is being carried out to retrieve two critically important terrestrial biophysical quantities (vegetation biomass and soil moisture) from remote sensing data using machine learning methods.

关键词： remote sensing soil moisture biomass retrieval algorithms machine learning artificial neural networks SVM regression biophysical parameters

来源：评论

学校读者我要写书评

暂无评论

GCOM-W1 AMSR2 and MetOp-A ASCAT wind speeds for the extratropical cyclones over the North Atlantic

引用

REMOTE SENSING OF ENVIRONMENT 2014年 147卷 89-98页

作者： Zabolotskikh, Elizaveta Mitnik, Leonid Chapron, Bertrand State Hydrometeorol Univ Satellite Oceanog Lab St Petersburg 195196 Russia VI Ilichev Pacific Oceanol Inst Vladivostok 690041 Russia IFREMER Ctr Brest F-29280 Plouzane France

This study presents the results of the comparison between sea surface wind speed (SWS) estimates made by MetOp-A scatterometer ASCAT and GCOM-W1 Advanced Microwave Sounding Radiometer 2 (AMSR2) relating to winds developing in the extratropical cyclones (ECs) over the North Atlantic. One season of winter ECs of 2012-2013 is considered in which 33 most intensive ECs are selected for the study. ASCAT Level 2 operational coastal wind vector product is used for the comparison, whereas AMSR2 SWS values are calculated with newly developed algorithms. Two algorithms for SWS retrieval from AMSR2 are based on numerical simulation of AMSR2 brightness temperatures (T-B) over the oceans and their following inversion with Neural Networks. The first algorithm uses T-B measurements at higher frequency AMSR2 channels (HF algorithm), the second one uses T-B measurements at lower frequency channels (LF algorithm). It is demonstrated that both AMSR2 SWS estimates are highly correlated with ASCAT SWS for the range of low and moderate wind speeds which opens new potential for possible merging of active and passive microwave SWS products. It is shown also that LF AMSR2 algorithm overestimates ASCAT winds greater than 15 m/s. To support the comparison results SWS estimates by AMSR2 are validated against in-situ wind speed measurements from platform weather stations in the North Sea and Norwegian Sea, including high wind events. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Active and passive sea surface wind speeds MetOp-A ASCAT GCOM-W1 AMSR2 retrieval algorithms Intercomparison Validation

来源：评论

学校读者我要写书评

暂无评论

Inter-comparison of Various Approaches of Ground-based Active Remote Sensing of Cloud Water Content 5

Inter-comparison of Various Approaches of Ground-based Activ...

引用

Conference on Remote Sensing of the Atmosphere, Clouds, and Precipitation V

作者： Wang, Qianqian Zhao, Chuanfeng Lv, Min Li, Zhanqing Beijing Normal Univ Coll Global Change & Earth Syst Sci Beijing 100875 Peoples R China

ISBN: (纸本)9781628413267

This paper provides an inter-comparison study of various ground-based cloud retrieval algorithms that have been developed to obtain cloud water content. The retrieval algorithms are classified into three types, statistical parameterization algorithm, physical retrieval algorithm, and optimal iteration method. Analyses indicate that physical retrieval algorithms are theoretically accurate, however, assumptions used in these methods make it challenging for them to obtain highly reliable results. Empirical parameterization methods are simple and can be easily applied. However, these methods are generally based on very limited cloud samples for certain types of clouds and locations, they have much larger uncertainties. In contrast, the optimal iteration method seems to have relatively higher accuracies since the retrieval results make the forward model simulations match observations. However, the accuracy of optimal iteration method is highly dependent on the reliability of the forward models and the a priori information.

关键词： inter-comparison ground-based retrieval algorithms liquid water content ice water content

来源：评论

学校读者我要写书评

暂无评论

Validation and potential applications of Environment Canada Ice Concentration Extractor (ECICE) algorithm to Arctic ice by combining AMSR-E and QuikSCAT observations

引用

REMOTE SENSING OF ENVIRONMENT 2013年 128卷 315-332页

作者： Shokr, Mohammed Agnew, Thomas A. Environm Canada Sci & Technol Branch Toronto ON M3H 5T4 Canada

The Environment Canada's Ice Concentration Extractor (ECICE) combines observations from several different satellite sensors to resolve heterogeneous components of a given footprint To validate the algorithm and demonstrate its applicability, results are presented from combining the enhanced AMSR-E 36.5 GHz passive microwave data with dual-polarization QuikSCAT active microwave scatterometer observations of Arctic ice during September to May;2007/08. Validation is performed using comparison with results from other algorithms in addition to operational ice charts. Three ice types are resolved: young, first-year and multiyear. Total ice concentration from ECICE under cold Arctic winter conditions is in agreement with estimates from previous algorithms such as the enhanced NASA Team. Distribution of multiyear ice concentration from ECICE is presented along with evolution of daily concentration of each ice type. Events of melt-refreeze, which are common during seasonal transition periods, cause misidentification of multiyear ice as first-year ice in the fall. The reverse is observed in the spring. This is a limitation on ice type identification. ECICE is an optimal approach that minimizes the error between observations and predicted concentrations. It provides a confidence measure associated with each ice concentration estimate. It is a generic algorithm, i.e. its applications are not limited to AMSR-E and QuikSCAT. Crown Copyright (C) 2012 Published by Elsevier Inc. All rights reserved.

关键词： Sea ice retrieval algorithms Ice concentration Arctic ice QuikSCAT AMSR-E Multiyear ice

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of the TRMM precipitation estimation using ground-based radars from the GPM validation network

引用

JOURNAL OF ATMOSPHERIC AND SOLAR-TERRESTRIAL PHYSICS 2012年 77卷 194-208页

作者： Islam, Tanvir Rico-Ramirez, Miguel A. Han, Dawei Srivastava, Prashant K. Ishak, Asnor M. Univ Bristol Dept Civil Engn Bristol Avon England

The Global Precipitation Measurement (GPM) mission is scheduled to fly in the year of 2013 to measure the earth's precipitation structure. Since the precipitation measurement by the GPM platform will be very similar to its predecessor, the Tropical Rainfall Measuring Mission (TRMM), hence, the development of GPM algorithms to improve precipitation retrievals can be addressed through the lessons learnt from the former TRMM mission in terms of precipitation retrievals and its associated uncertainty. To support the future GPM mission, this paper assesses the performance of the TRMM precipitation estimation using ground-based radars from the GPM validation network. A total of 22 significant overpass instantaneous events from 22 different radar sites has been evaluated in view of different surface and rain type flags. The overall results show that attenuation corrected reflectivity from the TRMM precipitation radar agrees well to the measured reflectivity from ground based radars with correlation coefficients r=0.91 (without frequency adjustment) and r=0.92 (with frequency adjustment). However, the correlation decreases by 10-30%, once the reflectivity are transformed to rainfall rates. The lower correlations on the basis of precipitation estimation by the TRMM are exhibited over the coast than those of ocean and land surface terrain. Taking into account the rain type flags, the analysis shows a poor correlation during convective precipitations, in particular, those retrieved from the TRMM precipitation radar. In contrast, the combined algorithm, which utilizes both radar and microwave imager instrument on-board TRMM, outperforms throughout the analysis, yet, there is a scope to improve the precipitation retrievals. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Microwave remote sensing Reflectivity Global rainfall Satellite mission Ground validation retrieval algorithms Active and passive NEXRAD (WSR-88D) Stratiform and convective Rainfall variability

来源：评论

学校读者我要写书评

暂无评论

ON THE USE OF MULTI-TEMPORAL SERIES OF COSMO-SKYMED DATA FOR LANDCOVER CLASSIFICATION AND SURFACE PARAMETER retrieval OVER AGRICULTURAL SITES

ON THE USE OF MULTI-TEMPORAL SERIES OF COSMO-SKYMED DATA FOR...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Balenzano, Anna Satalino, Giuseppe Belmonte, Antonella D'Urso, Guido Capodici, Fulvio Iacobellis, Vito Gioia, Andrea Rinaldi, Michele Ruggieri, Sergio Mattia, Francesco ISSIA CNR Bari Italy Univ Federico II Dipartimento Ingn Agraria Agronomia Territorio Bari Italy Politecn Bari PoliBa Dipartimento Ingegneria Acque Chim Bari Italy CRA SCA Consiglio Rice Sperimentazn Agr Bari Italy

ISBN: (纸本)9781457710056

The objective of this paper is to report on the activities carried out during the first year of the Italian project "Use of COSMO-SkyMed data for LANDcover classification and surface parameters retrieval over agricultural sites" (COSMOLAND), funded by the Italian Space Agency. The project intends to contribute to the COSMO-SkyMed mission objectives in the agriculture and hydrology application domains.

关键词： COSMO-SkyMed classification retrieval algorithms

来源：评论

学校读者我要写书评

暂无评论

SATELLITE SENSING OF INTENSE WINTER MESOCYCLONES OVER THE JAPAN SEA

SATELLITE SENSING OF INTENSE WINTER MESOCYCLONES OVER THE JA...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Mitnik, Leonid M. Gurvich, Irina A. Pichugin, Mikhail K. VI Ilichev Pacific Oceanol Inst FEB RAS Vladivostok 690041 Russia

ISBN: (纸本)9781457710056

Mesoscale cyclonic activity is one of the characteristics of the cold season in the Japan Sea. High winds and precipitation accompanying intense mesoscale cyclones (MCs) disturb transport and fishery operations in the sea and small sizes and fast development hinders their forecast and detection. Satellite data of visible, infrared, passive and active microwave sensors serve as a valuable source of data on MCs. They are used for their detection, tracking, evaluating of quantitative characteristics of the atmospheric and oceanic parameters during MC life cycle, getting statistical estimates as well as for checking and improving the results of modeling. Case studies demonstrate the efficiency of the multisensory approach and the leading role of microwave sensing for mesoscale cyclone investigation.

关键词： mesoscale cyclones passive microwave sensing Aqua AMSR-E retrieval algorithms Japan Sea

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：