87,943 Hits in 4.9 sec

A Lazy Approach for Efficient Index Learning [article]

Guanli Liu and Lars Kulik and Xingjun Ma and Jianzhong Qi
2021 arXiv   pre-print
We further show how our techniques can handle data updates and bound the resultant indexing errors.  ...  In this paper, we address the efficiency and update issues of learned indices through agile model reuse.  ...  Update handling. Updates may change the data distribution from which an index model is learned and amplify the model prediction error.  ... 
arXiv:2102.08081v2 fatcat:qw3ee3fokjexxjnvzcod6jwcha

An Online Stochastic Kernel Machine for Robust Signal Classification [article]

Raghu G. Raj
2019 arXiv   pre-print
We present a novel variation of online kernel machines in which we exploit a consensus based optimization mechanism to guide the evolution of decision functions drawn from a reproducing kernel Hilbert  ...  These results therefore demonstrate the importance of handling the non-stationary structure of labels (in addition to noise considerations) in the performance of an online inference algorithm.  ...  Furthermore, our results demonstrate the importance of handling the non-stationary structure of labels (in addition to noise considerations) in the performance of an online inference algorithm.  ... 
arXiv:1905.07686v2 fatcat:ctg7radssndhjhswpjnn2yutye

Online structure learning for robust object tracking

Liwei Liu, Junliang Xing, Haizhou Ai
2013 2013 IEEE International Conference on Image Processing  
In addition, OSMs guide the block occlusion reasoning and the update scheme of BORFs and relational models, which can handle appearance changes and drift problems effectively.  ...  To address these problems, we propose an online structure learning algorithm which contains two layers, block-based online random forest classifiers (BORFs) and online structure models (OSMs).  ...  In consideration of these problems, we introduce the structure models into the update scheme to adapt BORFs and relational models, which can handle appearance changes and occlusions very well.  ... 
doi:10.1109/icip.2013.6738805 dblp:conf/icip/LiuXA13 fatcat:ckaulla6kfcdde7eiqfb7os2tm

Hierarchical affinity hybrid tree: A multidimensional index structure to organize videos and support content-based retrievals

Kasturi Chatterjee, Shu-Ching Chen
2008 2008 IEEE International Conference on Information Reuse and Integration  
In this paper, we investigate the design of the second component, i.e., a multimedia index, and propose a novel tree-based multidimensional hierarchical index structure called Hierarchical Affinity Hybrid-Tree  ...  Data management techniques for traditional text-based data are inadequate to handle multimedia data efficiently due to their atypical characteristics.  ...  The matrices , F A, and B are constantly updated, for each iteration, through a learning process by utilizing users' feedback.  ... 
doi:10.1109/iri.2008.4583070 dblp:conf/iri/ChatterjeeC08 fatcat:anaxc636yrccja7ehti5ypx4my

Hands-off Model Integration in Spatial Index Structures [article]

Ali Hadian, Ankit Kumar, Thomas Heinis
2020 arXiv   pre-print
In this paper we thus explore the opportunity to use light-weight machine learning models to accelerate queries on spatial indexes.  ...  The plethora of indexes that has been developed in recent decades has primarily been optimised for disk.  ...  and also help in handling updates.  ... 
arXiv:2006.16411v2 fatcat:32c27kr555erbghggbaslzt7py

SCADS: Scale-Independent Storage for Social Computing Applications [article]

Michael Armbrust, David Patterson, Beth Trushkowsky (UC Berkeley), Jesse Trutna
2009 arXiv   pre-print
for relaxed consistency and pre-computed queries.  ...  allows the developer to declaratively state application specific consistency requirements, takes advantage of utility computing to provide cost effective scale-up and scale-down, and will use machine learning  ...  ACKNOWLEDGEMENTS We would like to thank the following people for their invaluable feedback on the ideas in this paper: Henry Cook, Mike Franklin, Jeff Hammerbacher, and John Ousterhout.  ... 
arXiv:0909.1775v1 fatcat:hn6psupmofgjhi473qzqberxwu

Tools and Methods for the Verification and Validation of Adaptive Aircraft Control Systems

Johann Schumann, Yan Liu
2007 2007 IEEE Aerospace Conference  
the validity index for the output of a Dynamic Cell Structure (DCS) network.  ...  We also discuss two monitoring tools for two types of neural networks employed in the NASA F-15 flight control system as adaptive learners: the confidence tool for the outputs of a Sigma-Pi network, and  ...  index for the output of a Dynamic Cell Structure (DCS) network.  ... 
doi:10.1109/aero.2007.352766 fatcat:jvbiw4wkm5cphg5wtm5fthw5iu


Giridhar Manepalli, Henry Jerez, Michael L. Nelson
2006 D-Lib Magazine  
FeDCOR (Federation of DSpace using CORDRA) is a registry-based federation system for DSpace instances. It is based on the CORDRA model. The first article in this issue of D-Lib  ...  [1] A software patch currently exists for DSpace that allows the use of remote handle servers. See <>. Notes  ...  for their knowledge sharing through their forums.  ... 
doi:10.1045/february2006-manepalli fatcat:d5x5usnkjbgzviuy3cfixisiya

Smart Adaptive Big Data Analysis with Advanced Deep Learning

Esko K. Juuso
2018 Open Engineering  
Artificial intelligence, deep learning, internet of things and cloud computing are proposed for heterogeneous datasets in hierarchical analytics to manage with the volume, variety, velocity and value of  ...  The advanced deep learning approach proposed in this paper uses generalized norms in feature generation, nonlinear scaling in developing compact indicators and linear interactions in model-based systems  ...  Acknowledgement: The author would like to thank the research program "Measurement, Monitoring and Environmental Efficiency Assesment (MMEA)" funded by the TEKES (the Finnish Funding Agency for Technology  ... 
doi:10.1515/eng-2018-0043 fatcat:mlocte7u7jbdzkmkmeds36npm4

Indexing of real time geospatial data by IoT enabled devices: Opportunities, challenges and design considerations

Natalia Chaudhry, Muhammad Murtaza Yousaf, Muhammad Taimoor Khan
2020 Journal of Ambient Intelligence and Smart Environments  
Some major challenges relevant to indexing of moving objects are highlighted. Various important index design considerations are also discussed.  ...  For example, in order for smartphones to correctly predict the directions they must have to embed spatial awareness within them.  ...  The discussion is focused on machine learning based methods for knowledge discovery in spatial databases.  ... 
doi:10.3233/ais-200565 fatcat:guzi2qgf4balhcvjnhlcnqjuru

Development of automatic intelligent system for on-line voltage security control of power systems

N. Tomin, A. Zhukov, V. Kurbatsky, D. Sidorov, M. Negnevitsky
2017 2017 IEEE Manchester PowerTech  
Therefore, several modified methods combined with machine learning algorithms enabling security assessment in real time have been proposed over the last years.  ...  In this case, the combination of original properties of PDSRF and capabilities of L-index as a target vector makes it possible to provide the functions of dispatcher warning, localization of critical nodes  ...  method can be to used for improving the voltage stability margin in real time using reactive power sources, generator excitation and on load tap changer transformers as controllers for different loading  ... 
doi:10.1109/ptc.2017.7980922 fatcat:5x5rielmb5aq3f6v5gszuel4oq

Integrating numerical and syntactic learning models for pattern recognition [chapter]

Terry Caelli
1998 Lecture Notes in Computer Science  
In this paper we consider how the recognition, interpretation of image structures, patterns, objects can be posed in terms of "Inductive Bayesian Networks" (IBN) which combine syntactic domain models with  ...  The net result of this formulation is the production of contextual and relational rules which can be used to summarize, generalize structural descriptions from examples in ways which are consistent with  ...  There are a number of fundamental problems with "attribute-indexed" or traditional Pattern Recognition (PR)/learning techniques: -They are not designed to index features as relational structure.  ... 
doi:10.1007/bfb0033228 fatcat:o6y5n2mo4zhjzdvjgh6uv2we3i

BYY harmony learning, independent state space, and generalized APT financial analyses

Lei Xu
2001 IEEE Transactions on Neural Networks  
for parameter learning, regularization and model selection, in both nontemporal and temporal stochastic environments.  ...  learning with automated model selection and parameter learning followed by model selection.  ...  by taking the term Tr in consideration for further adjustments.  ... 
doi:10.1109/72.935094 pmid:18249916 fatcat:sf4ghce6vjfmvmpcen7jekvhxa

Guest editorial: WWWJ special issue of the 20th international conference on Web information systems engineering (WISE 2019)

Reynold Cheng, Nikos Mamoulis, Xin Huang
2020 World wide web (Bussum)  
Special thanks to the journal editors for their great help and support in organizing the issue.  ...  To improve the performance of conditional queries, they build an AUP index and provide the AUP update solutions during transactions.  ...  A total of 211 research papers were submitted to the conference for consideration, and most of them were reviewed by three reviewers.  ... 
doi:10.1007/s11280-020-00853-4 fatcat:ttxwuox7z5ccrc4poee7lis5e4

PFO: A Parallel Friendly High Performance System for Online Query and Update of Nearest Neighbors [article]

Nan Zhu, Wenbo He, Xue Liu, Yu Hua
2016 arXiv   pre-print
PFO serves with higher throughput than the state-of-the-art LSH indexing structure when dealing with online query/update requests to nearest neighbors.  ...  In this paper, we propose a new LSH system called PFO. It handles query/update requests in RAM and scales the system capacity by using flash memory.  ...  DESIGN FOR HANDLING ONLINE UP-DATES The key point to accommodate the online updates is to apply the minimum change to the indexing structure when adding new data points.  ... 
arXiv:1604.06984v3 fatcat:sn6klys7cng2ngv7mkc76n2gke
« Previous Showing results 1 — 15 out of 87,943 results