Oumayma Jouini, K. Sethom, Abdallah Namoun, Nasser Aljohani, Meshari Huwaytim Alanazi, Mohammad N. Alanazi
{"title":"边缘计算中的机器学习概览:技术、框架、应用、问题和研究方向","authors":"Oumayma Jouini, K. Sethom, Abdallah Namoun, Nasser Aljohani, Meshari Huwaytim Alanazi, Mohammad N. Alanazi","doi":"10.3390/technologies12060081","DOIUrl":null,"url":null,"abstract":"Internet of Things (IoT) devices often operate with limited resources while interacting with users and their environment, generating a wealth of data. Machine learning models interpret such sensor data, enabling accurate predictions and informed decisions. However, the sheer volume of data from billions of devices can overwhelm networks, making traditional cloud data processing inefficient for IoT applications. This paper presents a comprehensive survey of recent advances in models, architectures, hardware, and design requirements for deploying machine learning on low-resource devices at the edge and in cloud networks. Prominent IoT devices tailored to integrate edge intelligence include Raspberry Pi, NVIDIA’s Jetson, Arduino Nano 33 BLE Sense, STM32 Microcontrollers, SparkFun Edge, Google Coral Dev Board, and Beaglebone AI. These devices are boosted with custom AI frameworks, such as TensorFlow Lite, OpenEI, Core ML, Caffe2, and MXNet, to empower ML and DL tasks (e.g., object detection and gesture recognition). Both traditional machine learning (e.g., random forest, logistic regression) and deep learning methods (e.g., ResNet-50, YOLOv4, LSTM) are deployed on devices, distributed edge, and distributed cloud computing. Moreover, we analyzed 1000 recent publications on “ML in IoT” from IEEE Xplore using support vector machine, random forest, and decision tree classifiers to identify emerging topics and application domains. Hot topics included big data, cloud, edge, multimedia, security, privacy, QoS, and activity recognition, while critical domains included industry, healthcare, agriculture, transportation, smart homes and cities, and assisted living. The major challenges hindering the implementation of edge machine learning include encrypting sensitive user data for security and privacy on edge devices, efficiently managing resources of edge nodes through distributed learning architectures, and balancing the energy limitations of edge devices and the energy demands of machine learning.","PeriodicalId":504839,"journal":{"name":"Technologies","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Survey of Machine Learning in Edge Computing: Techniques, Frameworks, Applications, Issues, and Research Directions\",\"authors\":\"Oumayma Jouini, K. Sethom, Abdallah Namoun, Nasser Aljohani, Meshari Huwaytim Alanazi, Mohammad N. Alanazi\",\"doi\":\"10.3390/technologies12060081\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Internet of Things (IoT) devices often operate with limited resources while interacting with users and their environment, generating a wealth of data. Machine learning models interpret such sensor data, enabling accurate predictions and informed decisions. However, the sheer volume of data from billions of devices can overwhelm networks, making traditional cloud data processing inefficient for IoT applications. This paper presents a comprehensive survey of recent advances in models, architectures, hardware, and design requirements for deploying machine learning on low-resource devices at the edge and in cloud networks. Prominent IoT devices tailored to integrate edge intelligence include Raspberry Pi, NVIDIA’s Jetson, Arduino Nano 33 BLE Sense, STM32 Microcontrollers, SparkFun Edge, Google Coral Dev Board, and Beaglebone AI. These devices are boosted with custom AI frameworks, such as TensorFlow Lite, OpenEI, Core ML, Caffe2, and MXNet, to empower ML and DL tasks (e.g., object detection and gesture recognition). Both traditional machine learning (e.g., random forest, logistic regression) and deep learning methods (e.g., ResNet-50, YOLOv4, LSTM) are deployed on devices, distributed edge, and distributed cloud computing. Moreover, we analyzed 1000 recent publications on “ML in IoT” from IEEE Xplore using support vector machine, random forest, and decision tree classifiers to identify emerging topics and application domains. Hot topics included big data, cloud, edge, multimedia, security, privacy, QoS, and activity recognition, while critical domains included industry, healthcare, agriculture, transportation, smart homes and cities, and assisted living. The major challenges hindering the implementation of edge machine learning include encrypting sensitive user data for security and privacy on edge devices, efficiently managing resources of edge nodes through distributed learning architectures, and balancing the energy limitations of edge devices and the energy demands of machine learning.\",\"PeriodicalId\":504839,\"journal\":{\"name\":\"Technologies\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-06-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Technologies\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/technologies12060081\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Technologies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/technologies12060081","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
物联网(IoT)设备通常在资源有限的情况下运行,同时与用户及其环境互动,产生大量数据。机器学习模型可以解释这些传感器数据,从而做出准确的预测和明智的决策。然而,来自数十亿设备的庞大数据量可能会使网络不堪重负,从而使传统的云数据处理在物联网应用中效率低下。本文全面介绍了在边缘和云网络的低资源设备上部署机器学习的模型、架构、硬件和设计要求方面的最新进展。为集成边缘智能而定制的著名物联网设备包括树莓派、英伟达的 Jetson、Arduino Nano 33 BLE Sense、STM32 微控制器、SparkFun Edge、Google Coral Dev Board 和 Beaglebone AI。这些设备都采用了定制的人工智能框架,如 TensorFlow Lite、OpenEI、Core ML、Caffe2 和 MXNet,以支持 ML 和 DL 任务(如物体检测和手势识别)。传统机器学习(如随机森林、逻辑回归)和深度学习方法(如 ResNet-50、YOLOv4、LSTM)都部署在设备、分布式边缘和分布式云计算上。此外,我们还使用支持向量机、随机森林和决策树分类器分析了 IEEE Xplore 上有关 "物联网中的 ML "的 1000 篇最新出版物,以确定新兴主题和应用领域。热门话题包括大数据、云、边缘、多媒体、安全、隐私、服务质量和活动识别,关键领域包括工业、医疗保健、农业、交通、智能家居和城市以及辅助生活。阻碍边缘机器学习实施的主要挑战包括在边缘设备上加密敏感的用户数据以确保安全和隐私,通过分布式学习架构有效管理边缘节点的资源,以及平衡边缘设备的能源限制和机器学习的能源需求。
A Survey of Machine Learning in Edge Computing: Techniques, Frameworks, Applications, Issues, and Research Directions
Internet of Things (IoT) devices often operate with limited resources while interacting with users and their environment, generating a wealth of data. Machine learning models interpret such sensor data, enabling accurate predictions and informed decisions. However, the sheer volume of data from billions of devices can overwhelm networks, making traditional cloud data processing inefficient for IoT applications. This paper presents a comprehensive survey of recent advances in models, architectures, hardware, and design requirements for deploying machine learning on low-resource devices at the edge and in cloud networks. Prominent IoT devices tailored to integrate edge intelligence include Raspberry Pi, NVIDIA’s Jetson, Arduino Nano 33 BLE Sense, STM32 Microcontrollers, SparkFun Edge, Google Coral Dev Board, and Beaglebone AI. These devices are boosted with custom AI frameworks, such as TensorFlow Lite, OpenEI, Core ML, Caffe2, and MXNet, to empower ML and DL tasks (e.g., object detection and gesture recognition). Both traditional machine learning (e.g., random forest, logistic regression) and deep learning methods (e.g., ResNet-50, YOLOv4, LSTM) are deployed on devices, distributed edge, and distributed cloud computing. Moreover, we analyzed 1000 recent publications on “ML in IoT” from IEEE Xplore using support vector machine, random forest, and decision tree classifiers to identify emerging topics and application domains. Hot topics included big data, cloud, edge, multimedia, security, privacy, QoS, and activity recognition, while critical domains included industry, healthcare, agriculture, transportation, smart homes and cities, and assisted living. The major challenges hindering the implementation of edge machine learning include encrypting sensitive user data for security and privacy on edge devices, efficiently managing resources of edge nodes through distributed learning architectures, and balancing the energy limitations of edge devices and the energy demands of machine learning.