检索结果-南通市图书馆

International Journal of Digital Earth 2023年第1期16卷 3618-3636页

作者： Gorica Bratic Vasil Yordanov Maria Antonia Brovelli Politecnico di Milano MilanItaly

There has been a significant increase in the availability of global high-resolution land cover(HRLC)datasets due to growing demand and favorable technological ***,this has brought forth the challenge of collecting reference data with a high level of detail for global *** photo-interpretation is considered optimal for collecting quality training data for global HRLC mapping,some producers of existing HRLCs use less trustworthy sources,such as existing land cover at a lower resolution,to reduce *** work proposes a methodology to extract the most accurate parts of existing HRLCs in response to the challenge of providing reliable reference data at a low *** methodology combines existing HRLCs by intersection,and the output represents a Map Of Land Cover Agreement(MOLCA)that can be utilized for selecting training ***’s effectiveness was demonstrated through HRLC map production in Africa,in which it generated 48,000 *** best classification test had an overall accuracy of 78%.This level of accuracy is comparable to or better than the accuracy of existing HRLCs obtained from more expensive sources of training data,such as photo-interpretation,highlighting the cost-effectiveness and reliability potential of the developed methodology in supporting global HRLC production.

关键词： High-resolution land cover global land cover training data reference data data quality

Consistency of the k-Nearest Neighbor Classifier for Spatially Dependent data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Communications in Mathematics and Statistics 2023年第3期11卷 503-518页

作者： Ahmad Younso Ziad Kanaya Nour Azhari INRAE Institut AgroMISTEAUniversitéMontpellierMontpellierFrance Department of Mathematical Statistics Faculty of SciencesDamascus UniversityDamascusSyria Department of Mathematics Faculty of SciencesTishreen UniversityLattakiaSyria

The purpose of this paper is to investigate the k-nearest neighbor classiﬁcation rule for spatially dependent *** spatial mixing conditions are considered,and under such spatial structures,the well known k-nearest neighbor rule is suggested to classify spatial *** established consistency and strong consistency of the classiﬁer under mild *** main results extend the consistency result in the *** to the spatial case.

关键词： Bayes rule Spatial data training data k-nearest neighbor rule Mixing condition Consistency

Blockchain for Education:Verification and Management of Lifelong Learning data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第11期43卷 591-604页

作者： Ba-Lam Do Van-Thanh Nguyen Hoang-Nam Dinh Thanh-Chung Dao BinhMinh Nguyen School of Information and Communication Technology Hanoi University of Science and TechnologyHanoiVietnam

In recent years,blockchain technology has been applied in the educational domain because of its salient advantages,i.e.,transparency,decentralization,and *** systems typically use public blockchain networks such as Ethereum and Bitcoin to store learning ***,the cost of writing data on these networks is significant,making educational institutions limit data sent to the target network,typically containing only hash codes of the issued *** this paper,we present a system based on a private blockchain network for lifelong learning data authentication and management named B4E(Blockchain For Education).B4E stores not only certificates but also learners’training data such as transcripts and educational programs in order to create a complete record of the lifelong education of each user and verify certificates that they have *** a result,B4E can address two types of fake certificates,i.e.,certificates printed by unlawful organizations and certificates issued by educational institutions for learners who have not met the training *** addition,B4E is designed to allow all participants to easily deploy software packages to manage,share,and check stored information without depending on a single point of *** such,the system enhances the transparency and reliability of the stored *** experiments show that B4E meets expectations for deployment in reality.

关键词： training data certificate verification and management private blockchain

Production of global land cover data-GLCNMO

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2011年第1期4卷 22-49页

作者： Ryutaro Tateishi Bayaer Uriyangqai Hussam Al-Bilbisi Mohamed Aboel Ghar Javzandulam Tsend-Ayush Toshiyuki Kobayashi Alimujiang Kasimu Nguyen Thanh Hoan Adel Shalaby Bayan Alsaaideh Tsevenge Enkhzaya Gegentana Hiroshi P.Sato Center for Environmental Remote Sensing(CEReS) Chiba UniversityChibaJapan College of Geographical Science Inner Mongolia Normal UniversityHuhhotChina Geography Department University of JordanAmmanJordan National Authority for Remote Sensing and Space Sciences(NARSS) CairoEgypt School of Computer and Information Technology Mongolian State University of EducationUlaanbaatarMongolia Institute of Geographical Science and Tourism Xinjiang Normal UniversityUrumqiChina Geographical Survey Institute TsukubaJapan

Global land cover is one of the fundamental contents of Digital *** Global Mapping project coordinated by the International Steering Committee for Global Mapping has produced a 1-km global land cover datasetGlobal Land Cover by National Mapping *** has 20 land cover classes defined using the Land Cover Classification *** them,14 classes were derived using supervised *** remaining six were classified independently:urban,tree open,mangrove,wetland,snow/ice,*** source data of this land cover mapping were eight periods of 16-day composite 7-band 1-km MODIS data of *** data for supervised classification were collected using Landsat images,MODIS NDVI seasonal change patterns,Google Earth,Virtual Earth,existing regional maps,and expert’s *** overall accuracy is 76.5%and the overall accuracy with the weight of the mapped area coverage is 81.2%.The data are available from the Global Mapping project website(http://***/).TheMODISdata used,land cover training data,and a list of existing regional maps are also available from the CEReS *** mapping attempt demonstrates that training/validation data accumulation from different mapping projects must be promoted to support future global land cover mapping.

关键词： land cover remote sensing Digital Earth training data

Highly accurate SVM model with automatic feature selection for word sense disambiguation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2004年第4期15卷 723-727页

作者： WangHao ChenGuilin XuLianxian DepartmentofComputerScienceandTechnology ShanghaiJiaotongUniversityShanghai200030P.R.China MotorolaChinaResearchCenter Shanghai200030P.R.China

A novel algorithm for word sense disambiguation(WSD) that is based on SVM model improved with automatic feature selection is introduced. This learning method employs rich contextual features to predict the proper senses for specific words. Experimental results show that this algorithm can achieve an execellent performance on the set of data released during the SENSEEVAL-2 competition. We present the results obtained and discuss the transplantation of this algorithm to other languages such as Chinese. Experimental results on Chinese corpus show that our algorithm achieves an accuracy of 70.0% even with small training data.

关键词： Support vector machines training data Accuracy Hidden Markov models Feature extraction Classification algorithms Context

NON-STATISTICAL TRANSFORMED data DOMAIN STAP ALGORITHM FOR NON-HOMOGENEOUS ENVIRONMENT

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

NON-STATISTICAL TRANSFORMED DATA DOMAIN STAP ALGORITHM FOR N...

2007 Asian and Pacific Conference on Synthetic Aperture Radar(APSAR 2007)

作者： Eunjung Yang Joohwan Chun Jonghoon Chun Division of Electrical Engineering Department of Electrical Engineering & Computer Science KAIST373-1 Gueseong-dongYuseong-guDaejeon 305-701Korea

ISBN: (纸本)1424411882;9781424411887

This paper introduces a new non-statistical STAP algorithm which is efficient and powerful in non-homogeneous environment. The traditional statistical algorithms using the estimated interference covariance are not optimal in heterogeneous clutter. The non-statistical approach which uses primary data only and is appropriate to extremely heterogeneous case is presented. The Transformed data Domain （TDD） algorithm which is more simple and efficient compared to the original Direct data Domain （D3） algorithm is proposed. The received space-time signal is transformed to beam-doppler domain and weight to minimize interferences is obtained in this space. The performance of the proposed non-statistical STAP is tested in SIRV clutter model environment and compared to that of the approach which employs traditional statistical algorithm.

关键词： training data Testing Clutter Interference suppression Covariance matrix Computer science Numerical simulation Random variables Statistical analysis Degradation

A Path Planning Method for Autonomous Ships Based on SVM

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Path Planning Method for Autonomous Ships Based on SVM

第32届中国控制与决策会议

作者： Shuanghu Qiao Kai Zheng Guofeng Wang Marine Electrical Engineering College Dalian Maritime University

Support vector machines（SVMs） are a set of related supervised learning methods,which can be used to solve the path planning problem of autonomous ships（ASs） with minimal *** addition to risk requirements,this paper aims to a potential requirement for the path length of ASs by using SVM *** with the conventional SVM methods for path planning which usually uses the boundaries of obstacles as training data,an expansion algorithm is proposed to redesign the training data so that the length of the path can be *** are carried out in the waters of Dalian to verify the effectiveness of the algorithm.

关键词： Autonomous ships Path planning Support vector machine training data

A NEW COMBINED MODELING OF CONTINUOUS SPEECH RECOGNITION

在线全文

cnki会议

学校读者我要写书评

暂无评论

A NEW COMBINED MODELING OF CONTINUOUS SPEECH RECOGNITION

2003 International Conference on Natural Language Processing and Knowledge Engineering

作者： Zhaobing HAN Lei JIA Shuwu Zhang Bo XU High-Tech Innovation Center Institute of AutomationChinese Academy of Science National Laboratory Of Pattern Recognition Institute of AutomationChinese Academy of Science

ISBN: (纸本)0780379020

＜正＞Robust estimate of a large number of parameters against the availability of training data is a crucial issue in triphone based continuous speech *** cope with the issue,two major context-clustering methods,agglomerative（AGG） and tree-based（TB）,have been widely *** this paper,we analyze two algorithms with respect to their advantages and disadvantages and introduce a novel combined method that takes advantage of each method to cluster and tie similar acoustic states for highly detailed acoustic *** addition,we devise a two-level clustering approach for TB,which uses the tree-based state tying for rare acoustic phonetic events *** LVCSR,the experimental results showed the performance could be highly improved by using the proposed combined method, compared with those of using the popular TB method alone.

关键词： speech recognition speech processing parameter estimation decision trees pattern clustering hidden Markov models parameter estimation training data triphone based continuous speech recognition context-clustering method agglomerative clustering acoustic phonetics decision tree hidden Markov models

Eigenfaces *** *** for Face Recognition;A Comparative Study

在线全文

cnki会议

学校读者我要写书评

暂无评论

2008 9th International Conference on Signal Processing(ICSP’2008)

作者： M.Sharkas M.Abou Elenien Arab Academy for Science and Technology-AAST Egypt

Face recognition issue gained more interest recently due to its various applications and the demand of high *** researches with contradicting results were published concerning this *** paper compared three popular face recognition projection methods:（eigenfaces）,（fisherfaces）,and *** also applied some data transformations:（Discrete Wavelet and cosine Transforms） preceding methods to see their *** researches based their results on the FERET *** and AT＆T databases were used here to see if the same results *** also compared the results of two sets of experiments with the second set using half the training images used in the first to observe if the results may *** conclusion is it can’t be stated that specific algorithm outperforms others,though ICA and Eigenfaces respectively showed better results than fisherfaces for both experiments sets and both *** algorithms with transformations yield better results for some algorithms.

关键词： Independent component analysis Face recognition Principal component analysis Linear discriminant analysis Application software Image databases Testing Discrete wavelet transforms training data Humans