161,237 Hits in 9.2 sec

Distribution Driven Extraction and Tracking of Features for Time-varying Data Analysis

Soumya Dutta, Han-Wei Shen
2016 IEEE Transactions on Visualization and Computer Graphics  
Effective analysis of features in time-varying data is essential in numerous scientific applications.  ...  In this work, we investigate these issues and propose a distribution driven approach which allows us to construct novel algorithms for reliable feature extraction and tracking with high confidence in the  ...  ACKNOWLEDGMENTS This work was supported in part by NSF grants IIS-1250752, IIS-1065025, and US Department of Energy grants DE-SC0007444, DE-DC0012495, program manager Lucy Nowell.  ... 
doi:10.1109/tvcg.2015.2467436 pmid:26529731 fatcat:2vfjq4tte5bobjzbkcywq62nvu

Information and Knowledge assisted analysis and Visualization of large-scale data

Chaoli Wang, Kwan-Liu Ma
2008 2008 Workshop on Ultrascale Visualization  
The ever-increasing sizes of data produced from a variety of scientific studies post a formidable challenge for the subsequent data analysis and visualization tasks.  ...  In many cases, the best interactivity can only be obtained by taking into account the intrinsic properties of the data and domain knowledge to better reduce and organize the data for visualization.  ...  Department of Energy through the SciDAC program with Agreement No. DE-FC02-06ER25777 and DE-FG02-08ER54956.  ... 
doi:10.1109/ultravis.2008.5154057 fatcat:ezo5zxlpsnhmbgj74nzrwdpwam

Parallel hypothesis driven video content analysis

Ole-Christoffer Granmo
2004 Proceedings of the 2004 ACM symposium on Applied computing - SAC '04  
Still, single-CPU Bayesian network systems for hypothesis driven feature extraction have been able to classify image content real-time -the expected information value and processing cost of features are  ...  Extraction of features from images, followed by pattern classification, is a promising approach to automatic video analysis.  ...  ACKNOWLEDGEMENTS I would like to thank Viktor Sigurd Wold Eide, Finn Verner Jensen, Frank Eliassen, and Olav Lysne for contributing to ideas presented in this paper.  ... 
doi:10.1145/967900.968035 dblp:conf/sac/Granmo04 fatcat:a6ya64ufvzbftksbaxqnideaq4

Systematic Literature Review on Data-Driven Models for Predictive Maintenance of Railway Track: Implications in Geotechnical Engineering

Jiawei Xie, Jinsong Huang, Cheng Zeng, Shui-Hua Jiang, Nathan Podlich
2020 Geosciences  
Conventional planning of maintenance and renewal work for railway track is based on heuristics and simple scheduling.  ...  This study presents a systematic literature review of data-driven models applied in the predictive maintenance of railway track.  ...  The emphasis is on the selection of appropriate feature extraction methods and data-driven models for different data sets, track defects, and maintenance strategies.  ... 
doi:10.3390/geosciences10110425 fatcat:r73zrv554vcsnjbi2aaeswvbsq

Modeling Trajectory-level Behaviors using Time Varying Pedestrian Movement Dynamics

Aniket Bera, Sujeong Kim, Dinesh Manocha
2018 Collective Dynamics  
We highlight the benefits of our approach on many indoor and outdoor scenarios with noisy, sparsely sampled trajectory in terms of trajectory prediction and data-driven pedestrian simulation.  ...  Our formulation extracts the dynamic behavior features of real-world agents and uses them to learn movement characteristics on the fly.  ...  Acknowledgements This work was supported by National Science Foundation award 1305286, ARO contract W911NF-16-1-0085, and a grant from the Boeing company.  ... 
doi:10.17815/cd.2018.15 fatcat:i74i7bbap5fcfez5nexgt7l3tm


2021 2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)  
Jun Hao, Guoshan Zhang 619 Rudder Health Monitoring and Data Visualization Based on Feature Extraction ………………………………………………….  ...  Control for a Class of Unknown Nonlinear Time-varying Systems Using Improved PID Neural Network and Cohen-coon Approach…………………………..……...  ... 
doi:10.1109/ddcls52934.2021.9455485 fatcat:7n7tpgqsuvg55og6dwwuj6g2xe

Dynamically Adaptive Tracking of Gestures and Facial Expressions [chapter]

D. Metaxas, G. Tsechpenakis, Z. Li, Y. Huang, A. Kanaujia
2006 Lecture Notes in Computer Science  
We present a dynamic data-driven framework for tracking gestures and facial expressions from monocular sequences.  ...  to the extracted 2D features.  ...  Experimental Results Summary and Conclusions We presented dynamic data-driven framework for tracking gestures and facial expressions from monocular sequences.  ... 
doi:10.1007/11758532_73 fatcat:26rujxnxivd7hhrwujzvx3skyq

Automatic analysis of time varying metrical structures in music

Kushagra Sharma, Ajay Srinivasamurthy, Xavier Serra
2017 Zenodo  
This thesis aims to infer and track the musical meter of such musical pieces by proposing extensions to a data driven Bayesian model which simultaneously infers the tempo, beats and downbeats of a musical  ...  In this thesis, we explore time varying metrical structures in music from the perspective of meter inference and tracking.  ...  It incorporates low-level feature extraction and high-level feature analysis based on machine learning methods.  ... 
doi:10.5281/zenodo.3770127 fatcat:cxg2d76vkbd33a37a27ifqxnyu

Hybrid Prognosis for Railway Health Assessment: An Information Fusion Approach for PHM Deployment

D. Galar, U. Kumar, R. Villarejo, C.A. Johansson
2013 Chemical Engineering Transactions  
A approach hybrid model can combine some or all model types (data-driven, and phenomenological); thus, more complete information can be gathered, leading to more accurate recognition of the fault state  ...  Broadly stated, prognostic methods are either data-driven or model-based. Each has advantages and disadvantages; consequently, they are often combined in hybrid applications.  ...  This paper is a modified version of a plenary keynote presented in CM 2013 and MFPT 2013, The Tenth International Conference on Condition Monitoring and Machinery Failure Prevention Technologies.  ... 
doi:10.3303/cet1333129 doaj:94c2d745f63e40ce896419d51597a0fe fatcat:t5ygpvite5gwjfvjhru27t6fdq

Pipeline for Tracking Neural Progenitor Cells [chapter]

Jacob S. Vestergaard, Anders L. Dahl, Peter Holm, Rasmus Larsen
2013 Lecture Notes in Computer Science  
Automated methods for neural stem cell lineage construction become increasingly important due to the large amount of data produced from time lapse imagery of in vitro cell growth experiments.  ...  We present here a tracking pipeline based on learning a dictionary of discriminative image patches for segmentation and a graph formulation of the cell matching problem incorporating topology changes and  ...  Acknowledgments The authors would like to thank laboratory technician Jytte Nielsen from Department of Basic Animal and Veterinary Sciences, Faculty of Life Sciences, Copenhagen University, for manual  ... 
doi:10.1007/978-3-642-36620-8_16 fatcat:qvty3gengff6zm6fmfszj5jte4

Scalable Independent Multi-level Distribution in Multimedia Content Analysis [chapter]

Viktor S. Wold Eide, Frank Eliassen, Ole-Christoffer Granmo, Olav Lysne
2002 Lecture Notes in Computer Science  
However, multimedia content analysis applications consist of multiple logical levels, such as streaming, filtering, feature extraction, and classification.  ...  Experiments demonstrate the scalability of a real-time motion vector based object tracking application implemented in the framework.  ...  For this purpose, we will add a parallelizable color feature extractor for more robust object tracking, i.e. objects can be identified and tracked based on color features.  ... 
doi:10.1007/3-540-36166-9_4 fatcat:7cajb57n45gs7ifrao6zosk2wy

Visualization and Analysis for Near-Real-Time Decision Making in Distributed Workflows

David Pugmire, James Kress, Jong Choi, Scott Klasky, Tahsin Kurc, Randy Michael Churchill, Matthew Wolf, Greg Eisenhower, Hank Childs, Kesheng Wu, Alexander Sim, Junmin Gu (+1 others)
2016 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)  
This paper discusses initial research into visualization and analysis of distributed data workflows that enables scientists to make nearreal-time decisions of large volumes of time varying data.  ...  Data driven science is becoming increasingly more common, complex, and is placing tremendous stresses on visualization and analysis frameworks.  ...  This serves as a demonstration of a significant step forward in accomplishing our goal of a data driven, nearreal-time, distributed visualization for a running simulation. VI.  ... 
doi:10.1109/ipdpsw.2016.175 dblp:conf/ipps/PugmireKCKKCWEC16 fatcat:yhdy6d4s6zap3b2klenwbzqlz4

An audio-driven dancing avatar

Ferda Ofli, Yasemin Demir, Yücel Yemez, Engin Erzin, A. Murat Tekalp, Koray Balcı, İdil Kızoğlu, Lale Akarun, Cristian Canton-Ferrer, Joëlle Tilmanne, Elif Bozkurt, A. Tanju Erdem
2008 Journal on Multimodal User Interfaces  
We present a framework for training and synthesis of an audio-driven dancing avatar. The avatar is trained for a given musical genre using the multicamera video recordings of a dance performance.  ...  The video is analyzed to capture the time-varying posture of the dancer's body  ...  SIMILAR, 3 by the Scientific and Technological Research Council of Turkey (TUBITAK) 4 under project EEEAG-106E201 and COST Action: 2102. 5 A.  ... 
doi:10.1007/s12193-008-0009-x fatcat:vnxmuu63rjgf3pvtgfcieh4lqq

Fault diagnosis of rotating machinery under time-varying speed based on order tracking and deep learning

Peng Wang, Taiyong Wang, Lan Zhang, Huihui Qiao
2020 Journal of Vibroengineering  
Due to the disadvantages that rely on prior knowledge and expert experience in traditional order analysis methods and deep learning cannot accurately extract the features in time-varying conditions.  ...  A fault diagnosis method for rotating machinery under time-varying conditions based on tacholess order tracking (TOT) and deep learning is proposed in this paper.  ...  Acknowledgements This paper is supported by National Natural Science Foundation of China (Grant No. 51975402  ... 
doi:10.21595/jve.2019.20784 fatcat:drsj6lc3vneyvctpuvsyxv4jue

Dynamic Tracking of Facial Expressions Using Adaptive, Overlapping Subspaces [chapter]

Dimitris Metaxas, Atul Kanaujia, Zhiguo Li
2007 Lecture Notes in Computer Science  
We use landmark based shape analysis to train a Gaussian mixture model over the aligned shapes and learn a Point Distribution Model(PDM) for each of the mixture components.  ...  The novelty of our approach is that the tracking of feature points is used to generate independent training examples for updating the learned shape manifold and the appearance model.  ...  Patent Pending The current technology is protected by patenting and trade marking office, "System and Method for Tracking Facial Features,", Atul Kanaujia and Dimitris Metaxas, Rutgers Docket 07-015, Provisional  ... 
doi:10.1007/978-3-540-72584-8_146 fatcat:5ouwpntcpbg4vdzsqiza774ydm
« Previous Showing results 1 — 15 out of 161,237 results