Filters








32,458 Hits in 4.9 sec

On Term Selection Techniques for Patent Prior Art Search

Mona Golestan Far, Scott Sanne, Mohamed Reda Bouadjenek, Gabriela Ferraro, David Hawking
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
We tried four simple automated approaches to identify negative terms for query reduction but we were unable to notably improve on the baseline performance with any of them.  ...  ) and BM25 scoring functions.  ...  Acknowledgments NICTA is funded by the Australian Government as represented by the Department of Broadband, Communications and the Digital Economy and the Australian Research Council through the ICT Centre  ... 
doi:10.1145/2766462.2767801 dblp:conf/sigir/FarSBFH15 fatcat:jrknhhhyungq3maltt5rztrly4

Constraint-Based Clustering Selection [article]

Toon Van Craenendonck, Hendrik Blockeel
2016 arXiv   pre-print
We empirically show that this simple approach often outperforms existing semi-supervised clustering methods.  ...  All of these approaches operate within the scope of individual clustering algorithms.  ...  / 2 http://www.ml.uni-saarland.de/code/cosc/cosc.htm Due to long runtimes of COSC, we do not report results in combination with CVCP on the two largest datasets (optdigits389 and segmentation).  ... 
arXiv:1609.07272v1 fatcat:6ixyemragfcp5gu4zbnol7omuy

Automation in the High-throughput Selection of Random Combinatorial Libraries—Different Approaches for Select Applications

Jörn Glökler, Tatjana Schütze, Zoltán Konthur
2010 Molecules  
Depending on scope, budget and time, a different combination of library and experimental handling might be most effective.  ...  Today, many combinatorial libraries as well as several systems for automation are available.  ...  Conclusions and Outlook We have successfully used a semi-automated approach for both phage display and SELEX.  ... 
doi:10.3390/molecules15042478 pmid:20428057 pmcid:PMC6257267 fatcat:b4hbd3x6mjdrpayxtr6b5finiy

Automated Domain-Specific Feature Selection for Classification-based Segmentation of Tomographic Medical Image Data

Gerald Zwettler, Werner Backfrieder
2017 International Journal of Privacy and Health Information Management  
The automated feature selection proofs to be accurate for classification-based segmentation utilizing well-known machine learning approaches.  ...  Predictability of both, single local and meta features, is evaluated for different medical datasets as well for simulated intensity volumes, allowing testing and evaluating specific classification problems  ...  While this approach is by far too user-intensive for practical application, the reference segmentations achievable in a semi-automated way are perfectly suited for training a priori models of specific  ... 
doi:10.4018/ijphim.2017010104 fatcat:enn54xdxbnejpaenkfierpjtx4

Constraint-based clustering selection

Toon Van Craenendonck, Hendrik Blockeel
2017 Machine Learning  
It turns out that this very simple approach outperforms all existing semi-supervised methods.  ...  In addition, the proposed approach allows for active constraint selection in a more effective manner than other methods.  ...  Toon Van Craenendonck is supported by the Agency for Innovation by Science and Technology in Flanders (IWT).  ... 
doi:10.1007/s10994-017-5643-7 fatcat:ckanpp3mvnfwzmgxhkzl2tv4xe

Selecting for Storage

Dan Hazen
2000 Library resources & technical services  
The most common approach to storage decisions begins with preselection based on circulation.  ...  LRTS 44(4) Practical Approaches to Selecting for Storage difficult for both librarians and library users.  ... 
doi:10.5860/lrts.44n4.176 fatcat:ym34rnqx4bcdrmgeyu5e55vuva

Automatic Virus Particle Selection—The Entropy Approach

Maria da Conceição M. Sangreman Proenca, J. F. Moura Nunes, A. P. Alves de Matos
2013 IEEE Transactions on Image Processing  
Morphological features help to select the candidates, as the threshold is kept low enough to avoid false negatives.  ...  This paper describes a fully automatic approach to locate icosahedral virus particles in transmission electron microscopy images.  ...  The semi-automated discrimination of certain gastro enteric viruses in the presence of others using bi-spectral features was tested in "a large set of negative stained EM images" [24] .  ... 
doi:10.1109/tip.2013.2244216 pmid:23380855 fatcat:qhlqydyptbeyzghi4pjma2as4i

PIXER: an automated particle-selection method based on segmentation using a deep neural network

Jingrong Zhang, Zihao Wang, Yu Chen, Renmin Han, Zhiyong Liu, Fei Sun, Fa Zhang
2019 BMC Bioinformatics  
The results indicate that, as a fully automated method, PIXER can acquire results as good as the semi-automated methods RELION and DeepEM.  ...  To free researchers from this laborious work and to acquire a large number of high-quality particles, we propose an automated particle-selection method (PIXER) based on the idea of segmentation using a  ...  The simulated data used in Section "Experiments on Simulated Data" can be found with accession code PDB-1F07. Authors' contributions JZ and FZ proposed the initial idea and designed the methodology.  ... 
doi:10.1186/s12859-019-2614-y fatcat:jov3b7xhfvafrozg6wjvo2nipq

Multi-atlas pancreas segmentation: Atlas selection based on vessel structure

Ken'ichi Karasawa, Masahiro Oda, Takayuki Kitasaka, Kazunari Misawa, Michitaka Fujiwara, Chengwen Chu, Guoyan Zheng, Daniel Rueckert, Kensaku Mori
2017 Medical Image Analysis  
Automated organ segmentation from medical images is an indispensable component for clinical applications such as computer-aided diagnosis (CAD) and computer-assisted surgery (CAS).  ...  Also, we investigate two types of applications of the vessel structure information to the atlas selection. Our segmentations were evaluated on 150 abdominal contrast-enhanced CT volumes.  ...  understanding and its application to computer-assisted diagnosis and surgery", and the Kayamori Foundation of Informational Science Advancement.  ... 
doi:10.1016/j.media.2017.03.006 pmid:28410505 fatcat:4vqifwfef5daxpbasdch5ga36y

EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation [article]

Bilwaj Gaonkar, Alex Bui, Luke Macyszyn
2019 arXiv   pre-print
We present our algorithm, followed by results and a discussion of how Eigenrank exploits the Von Neumann information to perform both data subset selection and failure prediction for medical image segmentation  ...  Translation of fully automated deep learning based medical image segmentation technologies to clinical workflows face two main algorithmic challenges.  ...  Our approach selects subsets which lead to the creation of deep learning models which are both more accurate and more robust than random selection.  ... 
arXiv:1908.06337v1 fatcat:7e7fah7f35hnlcrtn53vcqrrfq

Semi-Automatic Selection of Ground Control Points for High Resolution Remote Sensing Data in Urban Areas

Linda Gulbe, Gundars Korāts
2016 Applied Computer Systems  
Therefore, the aim of this study is to present and evaluate methodology for easier, semi-automatic selection of ground control points for urban areas.  ...  Manual selection of GCP is a time-consuming process, which requires some sort of automation.  ...  within the framework of Project No. 2/EEZLV02/14/GS/058 "Regional Strategy on Reduction of Greenhouse Gas Emissions from Buildings in Largest Cities in Kurzeme Planning Region, Using Satellite Imaging and  ... 
doi:10.1515/acss-2016-0011 fatcat:jbart4zxnnc3zadyqd4i4isgla

Selection and Application of Machine Learning- Algorithms in Production Quality [chapter]

Jonathan Krauß, Maik Frye, Gustavo Teodoro Döhler Beck, Robert H. Schmitt
2018 Technologien für die intelligente Automation  
Therefore we describe a promising approach how a decision making tool can help selecting ML-algorithms problem-specifically. J. Beyerer et al. (Eds.), für die intelligente Automation 9, https://doi.  ...  In this paper, we present a tangible use case in which MLalgorithms are applied for predicting the quality of products in a process chain and present the lessons learned we extracted from the application  ...  Lessons learned from the computer scientists and developers' perspective: Python notebooks like Jupyter are able to segment the entire code in sensible parts [17] .  ... 
doi:10.1007/978-3-662-58485-9_6 fatcat:hqvpnpwahrgwpoank3s6tqproa

2014 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 7

2014 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
., and Foerster, S  ...  ., +, JSTARS Dec. 2014 4849-4859 Performance evaluation A Methodology for Automated Segmentation and Reconstruction of Urban 3-D Buildings from ALS Point Clouds.  ...  ., +, JSTARS Dec. 2014 4869-4878 A Methodology for Automated Segmentation and Reconstruction of Urban 3-D Buildings from ALS Point Clouds.  ... 
doi:10.1109/jstars.2015.2397347 fatcat:ib3tjwsjsnd6ri6kkklq5ov37a

Deep Learning – A first Meta-Survey of selected Reviews across Scientific Disciplines and their Research Impact [article]

Jan Egger, Antonio Pepe, Christina Gsaxner, Jianning Li
2020 arXiv   pre-print
With these surveys as a foundation, the aim of this contribution is to provide a first high-level, categorized meta-analysis of selected reviews on deep learning across different scientific disciplines  ...  and outline the research impact that they already have during a short period of time.  ...  Moreover, they examined the most common datasets for answer selection and their evaluation metrics, and present various possible research directions for the future in this field.  ... 
arXiv:2011.08184v1 fatcat:7eofypvqordn7i4o7qmtoaaydi

End-to-End Content and Plan Selection for Data-to-Text Generation [article]

Sebastian Gehrmann, Falcon Z. Dai, Henry Elder, Alexander M. Rush
2018 arXiv   pre-print
Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG.  ...  An empirical evaluation of these techniques shows an increase in the quality of generated text across five automated metrics, as well as human evaluation.  ...  Since automated evaluation does not punish repeat sentences, we only enable this restriction when generating text for the human evaluation.  ... 
arXiv:1810.04700v1 fatcat:i3tvc5qaz5ehjhm6ivup6ncuhm
« Previous Showing results 1 — 15 out of 32,458 results