Filters








1,995 Hits in 7.4 sec

Multi-Component Optimization and Efficient Deployment of Neural-Networks on Resource-Constrained IoT Hardware [article]

Bharath Sudharsan, Dineshkumar Sundaram, Pankesh Patel, John G. Breslin, Muhammad Intizar Ali, Schahram Dustdar, Albert Zomaya, Rajiv Ranjan
2022 arXiv   pre-print
In this paper, to enable ultra-fast and accurate AI-based offline analytics on resource-constrained IoT devices, we present an end-to-end multi-component model optimization sequence and open-source its  ...  that can comfortably fit and execute on resource-constrained hardware.  ...  Neural Networks vs Resource-constrained MCUs.  ... 
arXiv:2204.10183v1 fatcat:7yelkcwgdvcg5n4t4tmwymsln4

Internet of Things (IoT) Operating Systems Management: Opportunities, Challenges, and Solution

Yousaf Bin Zikria, Sung Won Kim, Oliver Hahm, Muhammad Khalil Afzal, Mohammed Y. Aalsalem
2019 Sensors  
IoT requires to be intelligent to self-adapt according to the network conditions. In this paper, we present brief overview of different IoT OSs, supported hardware, and future research directions.  ...  Readily available low cost IoT hardware is essential for continuous adaptation of IoT.  ...  IoT devices are resource-constrained in terms of hardware resources and usually with limited battery capacity. Consequently, well known mature OS cannot be run on these devices.  ... 
doi:10.3390/s19081793 fatcat:kaxwclnfhvhrfgz23vzqacu5ni

Distributed Intelligence on the Edge-to-Cloud Continuum: A Systematic Literature Review

Daniel Rosendo, Alexandru Costan, Patrick Valduriez, Gabriel Antoniu
2022 Journal of Parallel and Distributed Computing  
applications;efficient deployment of Artificial Intelligence (AI) workflows on highly heterogeneous infrastructures; and reproducible analysis of experiments on the Computing Continuum.  ...  The large scale and optimized deployment of learning-based workflows across the Edge-to-Cloud Continuum requires extensive and reproducible experimental analysis of the application execution on representative  ...  Acknowledgments This work was funded by Inria through the HPC-BigData Inria Challenge (IPL) and by French ANR OverFlow project (ANR-15-CE25-0003).  ... 
doi:10.1016/j.jpdc.2022.04.004 fatcat:mopdegh4vrgt5k47vrmc7xum24

Machine Learning Systems for Intelligent Services in the IoT: A Survey [article]

Wiebke Toussaint, Aaron Yi Ding
2020 arXiv   pre-print
It covers the latest developments (up to 2020) on scaling and distributing ML across cloud, edge, and IoT devices.  ...  With a multi-layered framework to classify and illuminate system design choices, this survey exposes fundamental concerns of developing and deploying ML systems in the rising cloud-edge-device continuum  ...  CMSIS-NN [89] is an optimized library of software kernels to enable the deployment of neural networks on Cortex-M cores.  ... 
arXiv:2006.04950v3 fatcat:xrjcioqkrrhpvgmwmutiajgfbe

AI Augmented Edge and Fog Computing: Trends and Challenges [article]

Shreshth Tuli and Fatemeh Mirhakimi and Samodha Pallewatta and Syed Zawad and Giuliano Casale and Bahman Javadi and Feng Yan and Rajkumar Buyya and Nicholas R. Jennings
2022 arXiv   pre-print
Prior work focuses on improving existing systems using AI across a wide range of domains, such as efficient resource provisioning, application deployment, task placement, and service management.  ...  We present the latest trends and impact areas such as optimizing AI models that are deployed on or for computing systems.  ...  Scholarship at Imperial College London and Australian Research Council Discovery Project. We thank Shikhar Tuli, Zifeng Niu, Runan Wang, Matthew Sheldon and William Plumb for helpful discussions.  ... 
arXiv:2208.00761v1 fatcat:tfrhvlenyvbg7kidoydjzqejai

Time Series Network Data Enabling Distributed Intelligence. A Holistic IoT Security Platform Solution

Aikaterini Protogerou, Evangelos V. Kopsacheilis, Asterios Mpatziakas, Kostas Papachristou, Traianos Ioannis Theodorou, Stavros Papadopoulos, Anastasios Drosou, Dimitrios Tzovaras
2022 Electronics  
The implemented platform also includes the hypothesis testing module, and a multi-objective optimization tool for the quick verification of routing decisions.  ...  The aim of this paper is to present an efficient, robust, and easy-to-use system, for IoT cyber security operators.  ...  The opinions expressed in this paper are those of the authors and do not necessarily reflect the views of the European Commission.  ... 
doi:10.3390/electronics11040529 fatcat:m4tgpyvzhrft3i5loro3hememm

UNISENSE: A Unified and Sustainable Sensing and Transport Architecture for Large Scale and Heterogeneous Sensor Networks [chapter]

Yunye Jin, Hwee Pink Tan
2015 Complex Systems Design & Management Asia  
We describe the design and implementation for each component. We also present the deployment and performance of the UNISENSE architecture in four practical applications.  ...  The proposed architecture incorporates seven principal components, namely, application profiling, node architecture, intelligent network design, network management, deep sensing, generalized participatory  ...  We employ ideas from a recent advance of neural network technique called deep learning [8, 9] to improve the performance and derive actionable insights from the sensor network with limited resources.  ... 
doi:10.1007/978-3-319-12544-2_2 dblp:conf/csdm/JinT14 fatcat:ll3gsbcgvzgrfdibi2jchozaca

Bonseyes AI Pipeline – bringing AI to you. End-to-end integration of data, algorithms and deployment tools [article]

Miguel de Prado, Jing Su, Rabia Saeed, Lorenzo Keller, Noelia Vallez, Andrew Anderson, David Gregg, Luca Benini, Tim Llewellynn, Nabil Ouerhani, Rozenn Dahyot and, Nuria Pazos
2020 arXiv   pre-print
Our AI pipeline consists of four modular main steps: i) data ingestion, ii) model training, iii) deployment optimization and, iv) the IoT hub integration.  ...  However, training and deployment of custom AI solutions on embedded devices require a fine-grained integration of data, algorithms, and tools to achieve high accuracy.  ...  However, they are not efficient for deployment on resource-constrained devices.  ... 
arXiv:1901.05049v3 fatcat:dgs4zxtccne5nd4zvt4dqys44y

Machine Learning at the Network Edge: A Survey [article]

M.G. Sarwar Murshed, Christopher Murphy, Daqing Hou, Nazar Khan, Ganesh Ananthanarayanan, Faraz Hussain
2021 arXiv   pre-print
Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years.  ...  , frameworks, and hardware used in successful applications of intelligent edge systems.  ...  DNN-based keyword spotting systems are not easily deployable on resource-constrained devices.  ... 
arXiv:1908.00080v4 fatcat:mw4lwwvzf5gupjr6pgdgnabeuu

Enabling and Leveraging AI in the Intelligent Edge: A Review of Current Trends and Future Directions

Tom Goethals, Bruno Volckaert, Filip De Turck
2021 IEEE Open Journal of the Communications Society  
The use of AI in Smart applications and in the organization of the network edge presents a rapidly advancing research field, with a great variety of challenges and opportunities.  ...  This article aims to provide a holistic review of studies from 2019 to 2021 related to the Intelligent Edge, a concept comprising both the use of AI to organize edge networks (Edge Intelligence) and Smart  ...  The research in this paper has been funded by Vlaio by means of the FLEXNET research project.  ... 
doi:10.1109/ojcoms.2021.3116437 fatcat:knvl27fcwrarjhhua7zo475lwy

TinyML for Ubiquitous Edge AI [article]

Stanislava Soro
2021 arXiv   pre-print
TinyML addresses the challenges in designing power-efficient, compact deep neural network models, supporting software framework, and embedded hardware that will enable a wide range of customized, ubiquitous  ...  inference applications on battery-operated, resource-constrained devices.  ...  Challenges of Machine Learning on Embedded Devices Running complex machine learning models, such as neural networks on highly constrained embedded hardware requires careful software and hardware co-design  ... 
arXiv:2102.01255v1 fatcat:if5ny6kcirdkhnj56mswfaptlm

Fog Computing on Constrained Devices: Paving the Way for the Future IoT [article]

Flavia Pisani, Fabiola M. C. de Oliveira, Eduardo S. Gama, Roger Immich, Luiz F. Bittencourt, Edson Borin
2020 arXiv   pre-print
First, we present an overview of the concepts of constrained devices, IoT, and fog and mist computing, and then we present a classification of applications according to the amount of resources they require  ...  After that, we tie in these topics with a discussion of what can be expected in a future where constrained devices and fog computing are used to push the IoT to new limits.  ...  Acknowledgment The authors would like to thank CAPES and CNPq for the financial support.  ... 
arXiv:2002.05300v1 fatcat:ls7oppgcx5em3all3lfxymaofu

Machine Learning for Microcontroller-Class Hardware – A Review [article]

Swapnil Sayan Saha, Sandeep Singh Sandha, Mani Srivastava
2022 arXiv   pre-print
Conventional machine learning deployment has high memory and compute footprint hindering their direct deployment on ultra resource-constrained microcontrollers.  ...  Researchers use a specialized model development workflow for resource-limited applications to ensure the compute and latency budget is within the device limits while still maintaining the desired performance  ...  , and on-board sensor data analytics [4] [6] [7] on resource-constrained platforms.  ... 
arXiv:2205.14550v3 fatcat:y272riitirhwfgfiotlwv5i7nu

A Survey on Edge Computing Systems and Tools

Fang Liu, Guoming Tang, Youhuizi Li, Zhiping Cai, Xingzhou Zhang, Tongqing Zhou
2019 Proceedings of the IEEE  
Driven by the visions of Internet of Things and 5G communications, the edge computing systems integrate computing, storage and network resources at the edge of the network to provide computing infrastructure  ...  A comparison of open source tools is presented according to their applicability. Finally, we highlight energy efficiency and deep learning optimization of edge computing systems.  ...  It supports on-demand allocation and dynamic deployment of the multi-level architecture.  ... 
doi:10.1109/jproc.2019.2920341 fatcat:rocspx5ziffblfzaye2xhebe3e

Orchestrating the Development Lifecycle of Machine Learning-Based IoT Applications: A Taxonomy and Survey

Bin Qian, Jie Su, Zhenyu Wen, Devki Nandan Jha, Yinhao Li, Yu Guan, Deepak Puthal, Philip James, Renyu Yang, Albert Y. Zomaya, Omer Rana, Lizhe Wang (+2 others)
2020 ACM Computing Surveys  
Based on the specification and the available computing resources, the ML models are developed to meet the specified requirements while optimizing the training processes in terms of the cost of time and  ...  Additional Key Words and Phrases: IoT, Machine learning, Deep learning, Orchestration INTRODUCTION Rapid development of hardware, software and communication technologies boosts the speed of connection  ...  These neural networks optimize on-device inference performance via efficient design of building blocks, achieving much less computational complexity while keeping or even raising accuracy on various computer  ... 
doi:10.1145/3398020 fatcat:zzgfcjxjxbhnhf53dmlo63rs3i
« Previous Showing results 1 — 15 out of 1,995 results