453 Hits in 4.2 sec

Guest Editorial: IEEE TC Special Issue On Smart Edge Computing and IoT

Luca Benini, Simone Benatti, Taekwang Jang, Abbas Rahimi
2021 IEEE transactions on computers  
As a result, we witness a paradigm shift towards computationally demanding tasks on tiny form-factor devices at extreme energy efficiency.  ...  intelligence.  ...  The following papers mainly focused on the deployment of DNNs on IoT devices.  ... 
doi:10.1109/tc.2021.3082675 fatcat:ffx3cnnozbbivf5zokiil62irq

F1: Striking the Balance Between Energy Efficiency & Flexibility: General-Purpose vs Special-Purpose ML Processors

SukHwan Lim, Yong Pan Liu, Luca Benini, Tanay Karnik, Hsie-Chia Chang
2021 2021 IEEE International Solid- State Circuits Conference (ISSCC)  
to intelligent cloud.  ...  Neural Networks (NNs) have been widely employed in modern artificial intelligence (AI) systems due to their unprecedented capability in classification, recognition and detection.  ...  Though the research on hardware acceleration for neural networks has been extensively studied, the progress of hardware development still falls far behind the upscaling of DNN models at the software level  ... 
doi:10.1109/isscc42613.2021.9365804 fatcat:6qgx72c6bjcgndua43f4fsdggm

AI-Aided Integrated Terrestrial and Non-Terrestrial 6G Solutions for Sustainable Maritime Networking [article]

Salwa Saafi, Olga Vikhrova, Gábor Fodor, Jiri Hosek, Sergey Andreev
2022 arXiv   pre-print
To cope with the increased complexity of managing these integrated systems, this article advocates the use of artificial intelligence and machine learning-based approaches to meet the service requirements  ...  and energy efficiency targets in various maritime communications scenarios.  ...  This work was also supported by the Academy of Finland (projects Emc2-ML, RADIANT, and IDEA-MILL). G. Fodor was partially supported by the European Celtic project 6G-SKY with project ID C2021/1-9.  ... 
arXiv:2201.06947v2 fatcat:u7owlfpmz5f43jlbkvh2ztfvti

Efficient Edge-AI Application Deployment for FPGAs

Stavros Kalapothas, Georgios Flamis, Paris Kitsos
2022 Information  
This paper explores the efficacy and the dynamic deployment of hardware accelerated applications on the Kria KV260 development platform based on the Xilinx Kria K26 system-on-module (SoM), which includes  ...  Field Programmable Gate Array (FPGA) accelerators have been widely adopted for artificial intelligence (AI) applications on edge devices (Edge-AI) utilizing Deep Neural Networks (DNN) architectures.  ...  Institutional Review Board Statement: Not Applicable. Informed Consent Statement: Not applicable.  ... 
doi:10.3390/info13060279 fatcat:ecw2przphze6jltbk6wxtbstku

Predictive Quality of Service (PQoS): The Next Frontier for Fully Autonomous Systems [article]

Mate Boban, Marco Giordani, Michele Zorzi
2021 arXiv   pre-print
Recent advances in software, hardware, computing and control have fueled significant progress in the field of autonomous systems.  ...  Along these lines, in this paper we present possible methods to enable predictive QoS (PQoS) in autonomous systems, and discuss which use cases will particularly benefit from network prediction.  ...  Besides novel communication technologies and network architectures, the deployment of autonomous systems is accelerated by recent developments in the areas of artificial intelligence (AI) and machine learning  ... 
arXiv:2109.09376v1 fatcat:6sxycl55rjaxth6dtuhmcjvygu

An Overview of Federated Learning at the Edge and Distributed Ledger Technologies for Robotic and Autonomous Systems [article]

Yu Xianjia, Jorge Peña Queralta, Jukka Heikkonen, Tomi Westerlund
2021 arXiv   pre-print
At the same time, advances in deep learning (DL) have significantly raised the degree of autonomy and level of intelligence of robotic and autonomous systems.  ...  However, FL by itself does not provide the levels of security and robustness required by today's standards in distributed autonomous systems.  ...  to raise the level of autonomy and degree of intelligence of robotic systems.  ... 
arXiv:2104.10141v2 fatcat:x4mysoxyzzagpjxpzmpxu2af4q

6G Internet of Things: A Comprehensive Survey

Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, Dusit Niyato, Octavia Dobre, H. Vincent Poor
2021 IEEE Internet of Things Journal  
The sixth generation (6G) wireless communication networks are envisioned to revolutionize customer services and applications via the Internet of Things (IoT) towards a future of fully intelligent and autonomous  ...  systems.  ...  We believe our timely work will shed valuable light on the research of the 6G-IoT integration topics as well as motivate researchers and stakeholders to augment the research efforts in this promising area  ... 
doi:10.1109/jiot.2021.3103320 fatcat:fgm4ndqp6napjlt3z4ikthdsfy

A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones

Daniele Palossi, Antonio Loquercio, Francesco Conti, Francesco Conti, Eric Flamand, Eric Flamand, Davide Scaramuzza, Luca Benini, Luca Benini
2019 IEEE Internet of Things Journal  
Fully-autonomous miniaturized robots (e.g., drones), with artificial intelligence (AI) based visual navigation capabilities are extremely challenging drivers of Internet-of-Things edge intelligence capabilities  ...  In this work, we present the first (to the best of our knowledge) demonstration of a navigation engine for autonomous nano-drones capable of closed-loop end-to-end DNN-based visual navigation.  ...  Therefore, this section focuses on related work on nano-aircrafts [14] and the deployment of DNN on top of low-power IoT nodes.  ... 
doi:10.1109/jiot.2019.2917066 fatcat:ogqpf3qzg5hc5hph6cgdccivxu

A Deep Reinforcement Learning based Homeostatic System for Unmanned Position Control

Priyanthi M. Dassanayake, Ashiq Anjum, Warren Manning, Craig Bower
2019 Proceedings of the 6th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies - BDCAT '19  
The system is tested on a vehicle to autonomously re-position in an unpredictable environment. Our results show that the DRL based process control raised the accuracy of the hybrid model by 32%.  ...  In this paper, a mechanism to encapsulate the randomness of the environment is suggested using a novel bio-inspired homeostatic approach based on a hybrid of Receptor Density Algorithm (an artificial immune  ...  For deployments, depending on the specific environments the historical data may be used to structure the DNN. The complexity of the program may vary depending on the structure of DNN.  ... 
doi:10.1145/3365109.3368780 dblp:conf/bdc/DassanayakeAMB19 fatcat:skgwivyv3rhf7g2qx4bb3wa6c4

Artificial Intelligence for Enhanced Mobility and 5G Connectivity in UAV-Based Critical Missions

Silvia Lins, Kleber Cardoso, Cristiano Bonato Both, Luciano Mendes, Jose De Rezende, Antonio Silveira, Neiva Linder, Aldebaro Klautau
2021 IEEE Access  
The two parts of the partitioned DNN VOLUME X, XXXX were executed on Jetson Nano boards, which weigh 245 grams each.  ...  STANDARDIZED DEPLOYMENT OF EI AND SI EI requires two basic systems: (i) edge computing and (ii) network.  ...  intelligence using current and future standards, and an opensource testbed that can be used for research and development.  ... 
doi:10.1109/access.2021.3103041 fatcat:p4r7zswc7vbjtp37tctudwtpka

LENS: Layer Distribution Enabled Neural Architecture Search in Edge-Cloud Hierarchies [article]

Mohanad Odema, Nafiul Rashid, Berken Utku Demirel, Mohammad Abdullah Al Faruque
2021 arXiv   pre-print
Edge-Cloud hierarchical systems employing intelligence through Deep Neural Networks (DNNs) endure the dilemma of workload distribution within them.  ...  This paper addresses this issue for DNN architectural design by presenting a novel methodology, LENS, which administers multi-objective Neural Architecture Search (NAS) for two-tiered systems, where the  ...  In terms of DNNs, two approaches have been proposed to distribute their workloads in hybrid edge-cloud systems.  ... 
arXiv:2107.09309v1 fatcat:c3s6y6dl5fhoxdkmug2g6fkszi

Squeeze-and-Excitation SqueezeNext: An Efficient DNN for Hardware Deployment

Ravi Teja N.V.S Chappa, Mohamed El-Sharkawy
2020 2020 10th Annual Computing and Communication Workshop and Conference (CCWC)  
. • Requires the reduced model deployment on autonomous systems. • Needs rapid training and validating of CNN.  ...  There can be many tweaks be implemented on the existing architecture to make it more efficient for deployment on real-time systems.  ... 
doi:10.1109/ccwc47524.2020.9031119 dblp:conf/ccwc/ChappaE20 fatcat:dky2za3drbdmvm5cxnhgzl3xdy

Computational principles of intelligence: learning and reasoning with neural networks [article]

Abel Torres Montoya
2020 arXiv   pre-print
This work tries to contribute in this direction by proposing a novel framework of intelligence based on three principles.  ...  Despite significant achievements and current interest in machine learning and artificial intelligence, the quest for a theory of intelligence, allowing general and efficient problem solving, has done little  ...  On the other hand, intelligent systems can increase their knowledge towards the area containing the task's solution.  ... 
arXiv:2012.09477v1 fatcat:4gueufmj6zeozlf34zsccz7cfq

AI-Inspired Non-Terrestrial Networks for IIoT: Review on Enabling Technologies and Applications

Emmanouel T. Michailidis, Stelios M. Potirakis, Athanasios G. Kanatas
2020 IoT  
In this regard, this paper sheds light on the potential role of artificial intelligence (AI) techniques, including machine learning (ML) and deep learning (DL), in the provision of challenging NTN-based  ...  By adding intelligence and facilitating the decision-making and prediction procedures, the NTNs can effectively adapt to their surrounding environment, thus enhancing the performance of various metrics  ...  Airborne-Based Intelligent IIoT One of the main potential barriers of implementing airborne-based IIoT systems is the limited on-board capabilities of the aerial platforms that restrict their endurance  ... 
doi:10.3390/iot1010003 fatcat:xkjxfh6r2fd27jyuxazfc6lbqu

CLAN: Continuous Learning using Asynchronous Neuroevolution on Commodity Edge Devices [article]

Parth Mannan, Ananda Samajdar, Tushar Krishna
2020 arXiv   pre-print
Unfortunately, high compute and memory requirements of DNNs acts a huge barrier towards this vision.  ...  Recent advancements in machine learning algorithms, especially the development of Deep Neural Networks (DNNs) have transformed the landscape of Artificial Intelligence (AI).  ...  The use of BP again limits the deployment of RL on the edge. C.  ... 
arXiv:2008.11881v1 fatcat:al7pmoqwy5bafpdyspckbskb44
« Previous Showing results 1 — 15 out of 453 results