Filters








10 Hits in 1e+01 sec

A reusable pipeline for large-scale fiber segmentation on unidirectional fiber beds using fully convolutional neural networks [article]

Alexandre Fioravante de Siqueira and Daniela Mayumi Ushizima and Stéfan van der Walt
2021 arXiv   pre-print
To separate the fibers in these samples, we tested four different architectures of fully convolutional neural networks.  ...  When comparing our neural network approach to a semi-supervised one, we obtained Dice and Matthews coefficients greater than 92.28 ± 9.65%, reaching up to 98.42 ± 0.03 %, showing that the network results  ...  ACKNOWLEDGEMENTS AFS would like to thank Sebastian Berg, Ross Barnowski, Silvia Miramontes, Ralf Gommers, and Matt Rocklin for the discussions on fully convolutional networks, their structure and different  ... 
arXiv:2101.04823v2 fatcat:7lc3fldizzat5muzwrz4v7r2kq

IDEAL: Images Across Domains, Experiments, Algorithms and Learning

Daniela M. Ushizima, Hrishikesh A. Bale, E. Wes Bethel, Peter Ercius, Brett A. Helms, Harinarayan Krishnan, Lea T. Grinberg, Maciej Haranczyk, Alastair A. Macdowell, Katarzyna Odziomek, Dilworth Y. Parkinson, Talita Perciano (+2 others)
2016 JOM: The Member Journal of TMS  
This paper describes our algorithms and software tools, showing results across image scales, demonstrating how our framework plays a role in improving image understanding for quality control of existent  ...  Engineering tools around these efforts accelerate the analyses of image-based recordings, improve reusability and reproducibility, scale scientific procedures by reducing time between experiments, increase  ...  Recent work using convolutional neural networks as part of CBIR has proven useful for image retrieval across science domains. 33 To illustrate how these techniques can bring the ''faces of scientific  ... 
doi:10.1007/s11837-016-2098-4 fatcat:7vtt4az67fdbliuxcsdt3qqque

2020 Index IEEE Transactions on Industrial Informatics Vol. 16

2020 IEEE Transactions on Industrial Informatics  
Forests-Based Model for Ultra-Short-Term Prediction of PV Characteristics; TII Jan. 2020 202-214 Imran, A., see Hussain, B., TII Aug. 2020 4986-4996 Imran, M., see Fu, S., TII Sept. 2020 6013-6022  ...  see Daneshvar, M., TII June 2020 3928-3941 Mohtat, P., see Lee, S., TII May 2020 3376-3386 Momeni, H., Sadoogi, N., Farrokhifar, M., and Gharibeh, H.F., Fault Diagnosis in Photovoltaic Arrays Using  ...  Villalonga, A., +, TII Sept. 2020 5975-5984 Efficient Outdoor Video Semantic Segmentation Using Feedback-Based Fully Convolution Neural Network.  ... 
doi:10.1109/tii.2021.3053362 fatcat:blfvdtsc3fdstnk6qoaazskd3i

Program

2022 2022 International Conference on Decision Aid Sciences and Applications (DASA)  
A maximum of 92.90% classification accuracy is obtained using the features of IMF-4 with 10-fold cross-validation. The results conclude that the proposed method can detect AD patients efficiently.  ...  The proposed method can further be used to detect other neurological disorders.  ...  Keep the fact in mind, this paper presents a methodology for the identification of masks on people's faces using Convolution Neural Networks (CNN), for this, a training dataset has been used to generate  ... 
doi:10.1109/dasa54658.2022.9765271 fatcat:ttqppf4j3navnaxe653mrzmezi

D3.1 – State-of-the-Art and Market Analysis Report

ASSIST-IoT Consortium
2021 Zenodo  
A vehicle body inspection with the use of a Region-based Convolutional Neural Network (R-CNN) is suggested by for that purpose.  ...  large-scale.  ... 
doi:10.5281/zenodo.6705158 fatcat:xote6pjzubcvxo4aqxxbraooxi

Spoken command recognition for robotics [article]

BERTRAND HIGY
2019
The pipeline relies on a voice activity detection (VAD) system to propose a fully hand-free experience.  ...  The use of an attention-based encoder-decoder model reduced the classification error by 40% relative to a strong convolutional neural network (CNN)-hidden Markov model (HMM) baseline, showing the relevance  ...  The main limitation with the use of neural networks as language model (LM) though, also true for n-grams with a large context, is the computational cost.  ... 
doi:10.15167/higy-bertrand_phd2019-04-08 fatcat:zbcdjv6ns5hnrd4mj6yl6a5c34

Regensburger Applied Research Conference 2020 (RARC 2020), July 31st, 2020

Jürgen Mottok, Ingo Ehrlich, Anton Haumer
2020
Using a variety of online tools for teaching during this semester, we have enough experience to find a setup for RARC2020.  ...  However, for a Technical University the situation is rather a challenge than a problem.  ...  Thanks to Futonics Laser GmbH for providing a laser. ACKNOWLEDGMENT The author would like to thank Prof. Dr.-Ing. H.-P.  ... 
doi:10.35096/othr/pub-641 fatcat:pyqo2rcivfbnlnprjomti6dt64

UEG Week 2016 Oral Presentations

2016 United European Gastroenterology journal  
Intercellular space ratio and transepithelial electrical Foundation, and has served as consultant for Hitachi Medical Systems and AbbVie Inc. A.  ...  ., and Zambon for serving as a consultant and lecturer. L. Bergmann: Lars Bergmann is an employee of AbbVie Inc. and hold stock or stock options.  ...  A novel reusable endoscope (Olympus Corp.) with an integral motor was used for rotating a disposable short spiral overtube mounted on the insertion tube portion.  ... 
doi:10.1177/2050640616663688 fatcat:vlhrwp4txbewzj3arcu3hriifu

EMERGING 2011 The Third International Conference on Emerging Network Intelligence EMERGING 2011 Committee EMERGING Advisory Chairs

Tadashi Araragi, Tulin Atmaca, David Carrera, Robert Foster, Nuno Garcia, Raj Jain, Michael Logothetis, Krishna Murthy, Daniel Scheibli, Phuoc Tran-Gia, Raj Jain, Michael Logothetis (+25 others)
unpublished
Next-generation large distributed networks and systems require substantial reconsideration of exiting 'de facto' approaches and mechanisms to sustain an increasing demand on speed, scale, bandwidth, topology  ...  We hope that EMERGING 2011 was a successful international forum for the exchange of ideas and results between academia and industry and for the promotion of progress in emerging network intelligence.  ...  ACKNOWLEDGMENT We would like to thank Morten Laursen for contributing to the overall design, and I would also like to thank Esben Rasmussen and Claus Andersen for support in developing the imaging capture  ... 
fatcat:7p4e7qhc2zexxcj7vbfi6vd6ae

ICWMC 2017 Committee ICWMC Steering Committee ICWMC 2017 Technical Program Committee

Carlos Westphall, Khalil El-Khatib, Hamid Menouar, Carlos Westphall, Afrand Agah, West Chester, Pradipta De, David Sanchez, Carl Debono, Augusto Morales, Cheng Bo, Huawei Technologies (+64 others)
unpublished
on the previous events on advanced wireless technologies, wireless networking, and wireless applications.  ...  networks.  ...  ACKNOWLEDGMENT The authors would like to thank the Brazilian agencies CAPES (PROEX), CNPq and FAPEMIG for the financial support.  ... 
fatcat:hctrnh5xeng6tibh6stck62uui