8,296 Hits in 4.7 sec

Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation [article]

Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, Ken Sakurada
2021 arXiv   pre-print
This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable  ...  By using the developed module, the paper proposes heterogeneous grid convolutional networks, highly efficient yet strong extension of existing architectures.  ...  Acknowledgement This paper is partially based on results obtained from a project commissioned by the New Energy and Industrial Technology Development Organization (NEDO) and supported by JSPS KAKENHI Grant  ... 
arXiv:2104.11176v1 fatcat:4lkbvzvkgzadfe7dgqm6ah4sgq

Adaptive Surrogate Estimation with Spatial Features Using a Deep Convolutional Autoencoder for CO2 Geological Sequestration

Suryeom Jo, Changhyup Park, Dong-Woo Ryu, Seongin Ahn
2021 Energies  
This paper develops a reliable deep-learning framework to extract latent features from spatial properties and investigates adaptive surrogate estimation to sequester CO2 into heterogeneous deep saline  ...  Our deep-learning architecture includes a deep convolutional autoencoder (DCAE) and a fully-convolutional network to not only reduce computational costs but also to extract dimensionality-reduced features  ...  In addition, the large number of operations, e.g., dot products between the kernel and the feature map, and the training parameters decrease the computational efficiency; the computing cost of adaptive  ... 
doi:10.3390/en14020413 fatcat:ohapxmzzcjdlrk3aibt4at22pm

2020 Index IEEE Transactions on Industrial Informatics Vol. 16

2020 IEEE Transactions on Industrial Informatics  
-5149 Meng, K., see Zhang, Y., TII July 2020 4390-4402 Meng, K., Jia, Y., Yang, H., Niu, F., Wang, Y., and Sun, D., Motion Planning and Robust Control for the Endovascular Navigation of a Microrobot  ...  Moulay, E., Online GMM Clustering and Mini-Batch Gradient Descent Based Optimization for Industrial IoT 4.0; 1427-1435 Messina, F., see Fortino, G., TII Sept. 2020 6133-6142 Mi, C., see Zhu, C., TII  ...  ., +, TII April 2020 2707-2715 Digital signatures A Secure and Efficient Key Establishment Scheme for Communications of Smart Meters and Service Providers in Smart Grid.  ... 
doi:10.1109/tii.2021.3053362 fatcat:blfvdtsc3fdstnk6qoaazskd3i

Deep Learning for Real Time Crime Forecasting [article]

Bao Wang, Duo Zhang, Duanhao Zhang, P.Jeffery Brantingham, Andrea L. Bertozzi
2017 arXiv   pre-print
Second, we adapt hierarchical structures of residual convolutional units to train multi-factor crime prediction models.  ...  These distributions are of very low regularity in both space and time.  ...  Penghang Yin for fruitful discussions. This work was supported by ONR grant N00014-16-1-2119, ARO MURI grant W911NF-11-1-0332, NSF grants DMS-1118971 and DMS-1417674.  ... 
arXiv:1707.03340v1 fatcat:2vn7jp34fvhnzmddqfswuxwhku

Convolution Filtering of Continuous Signed Distance Fields for Polygonal Meshes

Mathieu Sanchez, Oleg Fryazinov, Pierre-Alain Fayolle, Alexander Pasko
2015 Computer graphics forum (Print)  
Several applications are presented such as blending, metamorphosis and heterogeneous modelling with polygonal meshes.  ...  The focus of this work is to efficiently evaluate the signed distance function and to apply a smoothing filter to it while preserving the shape of the initial mesh.  ...  The Stanford bunny model is courtesy of the Stanford University Computer Graphics Laboratory.  ... 
doi:10.1111/cgf.12599 fatcat:4ngdxkb6bbfftfi6552he4xhqq

2020 Index IEEE Transactions on Emerging Topics in Computational Intelligence Vol. 4

2020 IEEE Transactions on Emerging Topics in Computational Intelligence  
., +, TETCI Feb. 2020 23-31 Peer-to-peer computing Efficient Search and Lookup in Unstructured P2P Overlay Networks Inspired by Swarm Intelligence.  ...  Long, N.K., +, TETCI Aug. 2020 523-537 Telecommunication computing Deep Learning Based Hotspot Prediction and Beam Management for Adaptive Virtual Small Cell in 5G Networks.  ... 
doi:10.1109/tetci.2020.3042423 fatcat:qj6bpqfey5gpjhqe7zvgg644l4

Radioastronomy Image Synthesis on the Cell/B.E [chapter]

Ana Lucia Varbanescu, Alexander S. van Amesfoort, Tim Cornwell, Andrew Mattingly, Bruce G. Elmegreen, Rob van Nieuwpoort, Ger van Diepen, Henk Sips
2008 Lecture Notes in Computer Science  
In this paper, we analyze data gridding and degridding, a very time-consuming kernel of radioastronomy image synthesis.  ...  To tackle its its dynamic behavior, we devise and implement a parallelization strategy for the Cell/B.E. multi-core processor, offering a cost-efficient alternative compared to classical supercomputers  ...  We would like to thank Michael Perrone, Gordon Braudaway, Fabrizzio Petrini and Daniele Scarpazza for their valuable support and ideas during the development of this application.  ... 
doi:10.1007/978-3-540-85451-7_80 fatcat:26alc5c55re7tb4znyhmivytd4

An encoder-decoder deep surrogate for reverse time migration in seismic imaging under uncertainty [article]

Rodolfo S. M. Freitas, Carlos H. S. Barbosa, Gabriel M. Guerra, Alvaro L. G. A. Coutinho, Fernando A. Rochinha
2020 arXiv   pre-print
RTM, however, is time-consuming and data-intensive as it requires computing twice the wave equation to generate and store an imaging condition.  ...  Reverse time migration (RTM) is a high-resolution depth migration approach useful for extracting information such as reservoir localization and boundaries.  ...  This work is also partially supported by FAPERJ (grant E-26/203.018/2017), CNPq (grant 302489/2016-9), and Petrobras (grant 2017/00148-9).  ... 
arXiv:2006.09550v1 fatcat:45rkw3vapvfwhpi4xopa25ijlm

GPGPU Accelerated Deep Object Classification on a Heterogeneous Mobile Platform

Syed Rizvi, Gianpiero Cabodi, Denis Patti, Gianluca Francini
2016 Electronics  
Namely, the proposed approach relies on a heterogeneous CPU-GPU scheme for performing convolutions in the transform domain.  ...  The computational and memory requirements of such networks are however huge, and that is an issue on embedded devices due to their constraints.  ...  Acknowledgments: We would like to thank Attilio Fiandrotti and Skjalg Lepsoy for their helpful comments and suggestions.  ... 
doi:10.3390/electronics5040088 fatcat:oexwebv5wvarlomsmxihvvd2qi

Table of Contents

2020 IEEE Transactions on Industrial Informatics  
Bhuvaneswari 7349 Adaptive Discrete ZND Models for Tracking Control of Redundant Manipulator . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Maritime Search and Rescue Based on Group Mobile Computing for Unmanned Aerial Vehicles and Unmanned Surface Vehicles . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tii.2020.3022301 fatcat:7n2bzwx72bcencda27ey54zj6m

A Heterogeneous Multicore System on Chip for Energy Efficient Brain Inspired Computing

Antonio Pullini, Francesco Conti, Davide Rossi, Igor Loi, Michael Gautschi, Luca Benini
2018 IEEE Transactions on Circuits and Systems - II - Express Briefs  
Convolutional Neural Networks (CNNs) have revolutionized computer vision, speech recognition and other fields requiring strong classification capabilities.  ...  and peak performance of 14 GMAC/s @ 1.2V, leaving 1.2 GMAC/s available for generalpurpose parallel processing.  ...  As a way to understand how well convolutional layer execution (c) Efficiency of conv layer for HWCE and HWCE+MMUL while varying computation over communication ratio. 127 110 a For ASICs and Mia Wallace  ... 
doi:10.1109/tcsii.2017.2652982 fatcat:g4w6favd2bbcbomezvazbb3th4

Editorial for September 2020 issue

S. V. Raghavan
2020 CSI Transactions on ICT  
This novel system saves considerable computation resources of IoT devices and rapidly adapts to various data sources with different distortion levels.  ...  The authors also present an enhanced and efficient scheme, which is secure against Type 1, and Type II attacks and compare the proposed scheme with existing schemes in terms of computation and communication  ... 
doi:10.1007/s40012-020-00311-6 fatcat:pmkjtxqynfcrxb3sda7lhuxpga

ICUMT 2020 Table of Contents

2020 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)  
T 0 P ABCDEFGHILMNOPQRST_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ Technical Perspectives of Contact-Tracing Applications on Wearables for COVID-19 Control The Method and Methodology o f Efficiency Assessment  ...  a _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ S T Q P ABCDEFGHILMNOPQRST_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ SCADA-based Message Generator for Multi-Vendor Smart Grids: Integration and Verification  ... 
doi:10.1109/icumt51630.2020.9222452 fatcat:xlixcrofuvc4xefpf3zqms2gde

Papers by Title

2021 2021 International Conference on Advanced Technologies for Communications (ATC)  
Collision Avoidance Scheduling based on Traffic and Priority for IoT Sensor Networks Adaptive Sampling for Saving Energy: A Case Study on The Libelium-based Environment Monitoring Systems An Edge-AI Heterogeneous  ...  with TXOP-Bursting and AIFS Control Low-Latency and Secure Computation Offloading Assisted by Hybrid Relay-Reflecting Intelligent Surface Compressed Sensing Spectrum Reconstruction in Multi-Level Power  ... 
doi:10.1109/atc52653.2021.9598173 fatcat:ke4fex2jyvdjdhmczc73s2awfa

Detailed Technical Programme Schedule

2020 2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)  
Emerging Challenges in Distributed Energy Grid for Sustainable and , Ph.D., SMIEEE Professor, School of Computer Science and Engineering (Joint Appointment: School of IT Convergence) College of Information  ...  Technology, Waknaghat , Panipat Institute of Engineering and Technology, Panipat Emerging Challenges in Distributed Energy Grid for Sustainable and Appointment: School of 05.1: Distributed Computing,  ... 
doi:10.1109/pdgc50313.2020.9315322 fatcat:4ndwytytovb7xkntz7bmaurj6a
« Previous Showing results 1 — 15 out of 8,296 results