Suchergebnisse - "Edge TPU"

Heterogeneous Edge Computing for Molecular Property Prediction with Graph Convolutional Networks

Autoren: Grailootanha, Mahdieh Nunez-Yanez, Jose Luis

Quelle: Electronics. 14(1)

Schlagwörter: graph neural network, hardware accelerators, hardware/software co-design, FPGA HLS, streaming PYNQ overlay, Edge TPU, heterogeneous edge platform, molecular property prediction, molecular graph representation

Dateibeschreibung: electronic

Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-211073
https://doi.org/10.3390/electronics14010101

A Performance Prediction-based DNN Partitioner for Edge TPU Pipelining

Autoren: Zou, Bohua Sun, Binqi Hu, Yigong et al.

Weitere Verfasser: Zou, Bohua Sun, Binqi Hu, Yigong et al.

Quelle: MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM). :1-6

Schlagwörter: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Transformer, DNN Partition, DNN Partition Edge TPU Pipelining Transformer, Pipelining, Edge TPU, [INFO.INFO-ES] Computer Science [cs]/Embedded Systems

Dateibeschreibung: application/pdf

Optimal Model Placement in Heterogeneous Edge AI Environments

Autoren: Al-Bataineh, Bara Paradies, Marcus Dembska, Marta et al.

Quelle: Procedia Computer Science. 253:1903-1912

Schlagwörter: Optimization, Neural Network, Edge TPU, Edge AI, Model Placement

Zugangs-URL: https://elib.dlr.de/211457/
https://doi.org/10.1016/j.procs.2025.01.252

TPUXtract: An Exhaustive Hyperparameter Extraction Framework

Autoren: Ashley Kurian Anuj Dubey Ferhat Yaman et al.

Quelle: Transactions on Cryptographic Hardware and Embedded Systems, Vol 2025, Iss 1 (2024)

Schlagwörter: Hyperparameter, Machine Learning, TK7885-7895, Side Channel, Computer engineering. Computer hardware, Neural Networks, Information technology, Edge TPU, T58.5-58.64

Zugangs-URL: https://doaj.org/article/76de17c8c213458da972f02b861aa2d5

Plug, Play, Betray : Edge TPU Under Man-in-the-Middle Attack Colloque 2025 du GDR SoC2

Autoren: Niang, Seydina Oumar Lorandel, Jordane Moy, Christophe

Weitere Verfasser: Niang, Seydina Oumar Lorandel, Jordane Moy, Christophe

Schlagwörter: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Data exfiltration, USB security, Hardware vulnerability, Man-in-the-middle attack, Edge TPU, [INFO.INFO-ES] Computer Science [cs]/Embedded Systems

Dateibeschreibung: application/pdf

Zugangs-URL: https://hal.science/hal-05154900v1

Plug, Play, Betray : Edge TPU Under Man-in-the-Middle Attack Colloque 2025 du GDR SoC2

Autoren: Niang, S, O Lorandel, J Moy, C et al.

Weitere Verfasser: Niang, S, O Lorandel, J Moy, C et al.

Quelle: GDR SoC2 ; https://hal.science/hal-05154900 ; GDR SoC2, Jun 2025, Lorient, France

Schlagwörter: Data exfiltration, Hardware vulnerability, USB security, Man-in-the-middle attack, Edge TPU, [INFO.INFO-ES]Computer Science [cs]/Embedded Systems, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]

Geographisches Schlagwort: Lorient, France

Verfügbarkeit: https://hal.science/hal-05154900
https://hal.science/hal-05154900v1/document
https://hal.science/hal-05154900v1/file/Poster%20GDR%20SoC.pdf

Energy efficiency in edge TPU vs. embedded GPU for computer-aided medical imaging segmentation and classification

Autoren: Rodríguez Corral, José María Civit-Masot, Javier Luna Perejón, Francisco et al.

Weitere Verfasser: Rodríguez Corral, José María Civit-Masot, Javier Luna Perejón, Francisco et al.

Quelle: Engineering Applications of Artificial Intelligence Volume 127, Part B, January 2024, 107298.

Schlagwörter: Edge TPU, Embedded accelerated systems, Energy efficiency, GPU, Medical diagnostic aids

Dateibeschreibung: application/pdf

Relation: http://hdl.handle.net/10498/29776

Verfügbarkeit: http://hdl.handle.net/10498/29776
https://doi.org/10.1016/j.engappai.2023.107298

Impact of Mixed Precision Techniques on Training and Inference Efficiency of Deep Neural Networks

Autoren: Marion Dörrich Mingcheng Fan Andreas M. Kist

Quelle: IEEE Access, Vol 11, Pp 57627-57634 (2023)

Schlagwörter: green AI, edge TPU, Deep learning, quantization, Electrical engineering. Electronics. Nuclear engineering, mixed precision training, 7. Clean energy, energy efficiency, TK1-9971

Zugangs-URL: https://doaj.org/article/61ee2838b8e443b1bbf6d76b1a4cfa37

Partial Discharge Detection by Edge Computing

Autoren: Lukáš Klein Petr Žmij Pavel Krömer

Quelle: IEEE Access, Vol 11, Pp 44192-44204 (2023)

Schlagwörter: partial discharge, edge TPU, Edge computing, experiments, NVIDIA jetson, Electrical engineering. Electronics. Nuclear engineering, 15. Life on land, neural networks, TK1-9971

Zugangs-URL: https://doaj.org/article/48567f7ff7ca4e6abfab83b4909776f6

Scaling Spectrogram Data Representation for Deep Learning on Edge TPU

Autoren: Hosseininoorbin, Seyedehfaezeh Layeghy, Siamak Kusy, Brano et al.

Quelle: 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops). :572-578

Schlagwörter: IoT, Activity Classification, Joint Time-frequency Data Representation, 0202 electrical engineering, electronic engineering, information engineering, Edge Machine Learning, 02 engineering and technology, Edge TPU, 7. Clean energy

Dateibeschreibung: application/pdf

Construction Jobsite Image Classification Using an Edge Computing Framework

Autoren: Gongfan Chen Abdullah Alsharef Edward Jaselskis

Quelle: Sensors, Vol 24, Iss 20, p 6603 (2024)

Schlagwörter: edge computing, construction image classification, quantization, transfer learning, Raspberry Pi, Edge TPU, Chemical technology, TP1-1185

Dateibeschreibung: electronic resource

Relation: https://www.mdpi.com/1424-8220/24/20/6603; https://doaj.org/toc/1424-8220

Zugangs-URL: https://doaj.org/article/d1420c4e298b4df9b2641b2fe2c55fe5

HARBIC: Human Activity Recognition Using Bi-Stream Convolutional Neural Network with Dual Joint Time-Frequency Representation

Autoren: Hosseininoorbin, Seyedehfaezeh Layeghy, Siamak Kusy, Brano et al.

Weitere Verfasser: Hosseininoorbin, Seyedehfaezeh Layeghy, Siamak Kusy, Brano et al.

Quelle: Internet of Things (Netherlands)

Schlagwörter: Edge deep learning, Edge TPU, Human activity recognition, IoT, Joint time–frequency data representation

Dateibeschreibung: application/pdf

Relation: https://eprints.qut.edu.au/239590/8/HARBIC.pdf; https://eprints.qut.edu.au/239590/

Verfügbarkeit: https://doi.org/10.1016/j.iot.2023.100816
https://eprints.qut.edu.au/239590/

ROBUST HYPERSPHERE-BASED WEIGHT IMPRINTING FOR FEW-SHOT LEARNING

Autoren: Passalis, Nikolaos Iosifidis, Alexandros Gabbouj, Moncef et al.

Weitere Verfasser: Passalis, Nikolaos Iosifidis, Alexandros Gabbouj, Moncef et al.

Quelle: 2020 28th European Signal Processing Conference (EUSIPCO)
https://hal.archives-ouvertes.fr/hal-03265186
2020 28th European Signal Processing Conference (EUSIPCO), Jan 2021, Amsterdam (virtual), Netherlands. ⟨10.23919/Eusipco47968.2020.9287340⟩

Schlagwörter: Weight Imprinting, Few-shot Learning, Edge TPU, Embedded Deep Learning, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]

Geographisches Schlagwort: Amsterdam (virtual), Netherlands

Relation: hal-03265186; https://hal.archives-ouvertes.fr/hal-03265186; https://hal.archives-ouvertes.fr/hal-03265186/document; https://hal.archives-ouvertes.fr/hal-03265186/file/Robust%20Hypersphere-based%20Weight%20Imprinting%20for%20Few-shot%20Learning.pdf

Verfügbarkeit: https://hal.archives-ouvertes.fr/hal-03265186
https://hal.archives-ouvertes.fr/hal-03265186/document
https://hal.archives-ouvertes.fr/hal-03265186/file/Robust%20Hypersphere-based%20Weight%20Imprinting%20for%20Few-shot%20Learning.pdf
https://doi.org/10.23919/Eusipco47968.2020.9287340

Using Cutting Edge Software and Techniques to Model and Measure Experimental Neutrino Data

Autoren: Vergani, Stefano

Schlagwörter: dune, neutrino, pandora, machine learning, sterile neutrino, edge tpu, deep learning, particle physics, artificial intelligence, miniboone, protodune, physics

Energy efficiency in Edge TPU vs. embedded GPU for computer-aided medical imaging segmentation and classification

Autoren: Rodríguez Corral, José María Civit-Masot, Javier Luna Perejón, Francisco et al.

Weitere Verfasser: Rodríguez Corral, José María Civit-Masot, Javier Luna Perejón, Francisco et al.

Quelle: Engineering Applications of Artificial Intelligence, Volume 127, Part B, 2024, 107298.

Schlagwörter: Edge TPU, embedded accelerated systems, energy efficiency, GPU, medical diagnostic aids

Dateibeschreibung: application/pdf

Relation: http://hdl.handle.net/10498/29609

Verfügbarkeit: http://hdl.handle.net/10498/29609

A study on the use of Edge TPUs for eye fundus image segmentation

Autoren: Civit-Masot, Javier Luna Perejón, Francisco Rodríguez Corral, José María et al.

Weitere Verfasser: Civit-Masot, Javier Luna Perejón, Francisco Rodríguez Corral, José María et al.

Quelle: Engineering Applications of Artificial Intelligence, Volume 104, 2021, 104384.

Schlagwörter: Deep Learning, Edge TPU, Medical image segmentation, Glaucoma, Single-board computer, U-Net

Dateibeschreibung: application/pdf

Relation: info:eu-repo/grantAgreement/AEI//EQC2018-005190-P; http://hdl.handle.net/10498/29624

Verfügbarkeit: http://hdl.handle.net/10498/29624
https://doi.org/10.1016/j.engappai.2021.104384

A study on the use of Edge TPUs for eye fundus image segmentation

Autoren: Civit Masot, Javier Luna Perejón, Francisco Rodríguez Corral, José María et al.

Weitere Verfasser: Civit Masot, Javier Luna Perejón, Francisco Rodríguez Corral, José María et al.

Schlagwörter: Deep learning, Edge TPU, Medical image segmentation, Glaucoma, Single-board computer, U-Net

Relation: Engineering Applications of Artificial Intelligence, 104 (September 2021, art. nº104384); EQC2018-005190-P; https://www.sciencedirect.com/science/article/pii/S0952197621002323?via%3Dihub; https://idus.us.es/handle//11441/135624

Verfügbarkeit: https://idus.us.es/handle//11441/135624

Performance and Power Consumption Measurement and Analysis of Edge Computing Devices

Autoren: YUAN Jiawei, SONG Qingzeng, WANG Xuechun, JIANG Wenchao, JIN Guanghao

Quelle: Jisuanji gongcheng, Vol 47, Iss 2, Pp 233-238,245 (2021)

Schlagwörter: edge computing, edge tpu computing board, graphics processing unit(gpu), roofline model, field programmable gate array(fpga), Computer engineering. Computer hardware, TK7885-7895, Computer software, QA76.75-76.765

Dateibeschreibung: electronic resource

Relation: https://www.ecice06.com/fileup/1000-3428/PDF/20210234.pdf; https://doaj.org/toc/1000-3428

Zugangs-URL: https://doaj.org/article/9e5ab64374204726b58ff725eb162692

Highly-Optimized Radar-Based Gesture Recognition System with Depthwise Expansion Module

Autoren: Chmurski, Mateusz Mauro, Gianfranco Santra, Avik et al.

Schlagwörter: Edge computing, Edge TPU, Optimization, Quantization, FMCW, Radar, Deep learning, Neural networks

Relation: http://hdl.handle.net/10481/71388

Verfügbarkeit: http://hdl.handle.net/10481/71388
https://doi.org/10.3390/s21217298

Hypersphere-Based Weight Imprinting for Few-Shot Learning on Embedded Devices

Autoren: Passalis, Nikolaos Iosifidis, Alexandros Gabbouj, Moncef et al.

Weitere Verfasser: Passalis, Nikolaos Iosifidis, Alexandros Gabbouj, Moncef et al.

Quelle: ISSN: 2162-237X ; IEEE Transactions on Neural Networks and Learning Systems ; https://hal.archives-ouvertes.fr/hal-03265179 ; IEEE Transactions on Neural Networks and Learning Systems, IEEE, 2021, 32 (2), pp.925-930. ⟨10.1109/TNNLS.2020.2979745⟩.

Schlagwörter: Weight Imprinting, Few-shot Learning, Edge TPU, Embedded Deep Learning, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]

Relation: hal-03265179; https://hal.archives-ouvertes.fr/hal-03265179; https://hal.archives-ouvertes.fr/hal-03265179/document; https://hal.archives-ouvertes.fr/hal-03265179/file/Hypersphere-Based%20Weight%20Imprinting%20for%20Few-Shot%20Learning%20on%20Embedded%20Devices.pdf

Verfügbarkeit: https://hal.archives-ouvertes.fr/hal-03265179
https://hal.archives-ouvertes.fr/hal-03265179/document
https://hal.archives-ouvertes.fr/hal-03265179/file/Hypersphere-Based%20Weight%20Imprinting%20for%20Few-Shot%20Learning%20on%20Embedded%20Devices.pdf
https://doi.org/10.1109/TNNLS.2020.2979745