TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities

Sánchez-Iborra, Ramón; Skarmeta, Antonio F.

doi:10.1109/mcas.2020.3005467

Cited by 221 publications

(113 citation statements)

References 29 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…This has thus opened a growing research area in embedded machine learning termed TinyML. TinyML is a machine learning technique that integrates compressed and optimized machine learning to suit very low-power MCUs [ 141 ]. TinyML primarily differs from cloud machine learning (where compute intensive models are implemented using high-end computers in large datacenters like Facebook [ 142 ]), Mobile machine learning in terms of their very low power consumption (averagely 0.1 W) as shown in Table 15 .…”

Section: Machine Learning In Resource-constrained Environmentsmentioning

confidence: 99%

“…TinyML primarily differs from cloud machine learning (where compute intensive models are implemented using high-end computers in large datacenters like Facebook [ 142 ]), Mobile machine learning in terms of their very low power consumption (averagely 0.1 W) as shown in Table 15 . TinyML creates a platform whereby machine learning models are pushed to user devices to inform good user experience for diverse applications and it has advantages such as energy efficiency, reduced costs, data security, low latency, etc., which are major concerns in contemporary cloud computing technology [ 141 ]. Colby et al [ 143 ] presented a survey where neural network architectures (MicroNets) target commodity microcontroller units.…”

Section: Machine Learning In Resource-constrained Environmentsmentioning

confidence: 99%

See 1 more Smart Citation

An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

Ajani

Imoize

Atayero

2021

Sensors

105

View full text Add to dashboard Cite

Embedded systems technology is undergoing a phase of transformation owing to the novel advancements in computer architecture and the breakthroughs in machine learning applications. The areas of applications of embedded machine learning (EML) include accurate computer vision schemes, reliable speech recognition, innovative healthcare, robotics, and more. However, there exists a critical drawback in the efficient implementation of ML algorithms targeting embedded applications. Machine learning algorithms are generally computationally and memory intensive, making them unsuitable for resource-constrained environments such as embedded and mobile devices. In order to efficiently implement these compute and memory-intensive algorithms within the embedded and mobile computing space, innovative optimization techniques are required at the algorithm and hardware levels. To this end, this survey aims at exploring current research trends within this circumference. First, we present a brief overview of compute intensive machine learning algorithms such as hidden Markov models (HMM), k-nearest neighbors (k-NNs), support vector machines (SVMs), Gaussian mixture models (GMMs), and deep neural networks (DNNs). Furthermore, we consider different optimization techniques currently adopted to squeeze these computational and memory-intensive algorithms within resource-limited embedded and mobile environments. Additionally, we discuss the implementation of these algorithms in microcontroller units, mobile devices, and hardware accelerators. Conclusively, we give a comprehensive overview of key application areas of EML technology, point out key research directions and highlight key take-away lessons for future research exploration in the embedded machine learning domain.

show abstract

Section: Machine Learning In Resource-constrained Environmentsmentioning

confidence: 99%

Section: Machine Learning In Resource-constrained Environmentsmentioning

confidence: 99%

An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

Ajani

Imoize

Atayero

2021

Sensors

105

View full text Add to dashboard Cite

show abstract

“…As an emerging AI sub-field, TinyML is dedicated to providing neural network-based solutions at the edge. Impressive results have been achieved recently, such as tinyML algorithm [32][25], hardware [10][9], and application [34] [5]. Several libraries are developed to support NN inference at the edge, including Google's TFLite Micro [17], Arm's CMSIS-NN [26], Apache's TVM [18], and STM's X-CUBE-STM AI [36].…”

Section: Related Workmentioning

confidence: 99%

The synergy of complex event processing and tiny machine learning in industrial IoT

Ren

Anicic

Runkler

2021

Proceedings of the 15th ACM International Conference on Distributed and Event-Based Systems

View full text Add to dashboard Cite

Focusing on comprehensive networking, the Industrial Internetof-Things (IIoT) facilitates efficiency and robustness in factory operations. Various intelligent sensors play a central role, as they generate a vast amount of real-time data that can provide insights into manufacturing. Complex event processing (CEP) and machine learning (ML) have been developed actively in the last years in IIoT to identify patterns in heterogeneous data streams and fuse raw data into tangible facts. In a traditional compute-centric paradigm, the raw field data are continuously sent to the cloud and processed centrally. As IIoT devices become increasingly pervasive, concerns are raised since transmitting such an amount of data is energy-intensive, vulnerable to be intercepted, and subjected to high latency. Decentralized on-device ML and CEP provide a solution where data is processed primarily on edge devices. Thus communications can be minimized. However, this is no mean feat because most IIoT edge devices are resource-constrained with low power consumption. This paper proposes a framework that exploits ML and CEP's synergy at the edge in distributed sensor networks. By leveraging tiny ML and µCEP, we now shift the computation from the cloud to the resource-constrained IIoT devices and allow users to adapt on-device ML models and CEP reasoning rules flexibly on the fly. Lastly, we demonstrate the proposed solution and show its effectiveness and feasibility using an industrial use case of machine safety monitoring. CCS CONCEPTS• Computing methodologies → Machine learning approaches; • Computer systems organization → Real-time systems; Sensor networks; • Information systems → Data streaming.

show abstract

“…The new trend, referred to as TinyML [9], of equipping IoT end-devices with capabilities to execute Machine Learning (ML) algorithms paves the way for a wide plethora of innovative intelligent applications and services, and contributes to the radical IoT shift from connected things to connected intelligent things, which is at the basis of future sixth generation (6G) systems [10]. TinyML is getting close to reality thanks to recent advancements in the miniaturization of AI-optimized processors and the definition of extremely lightweight ML inference frameworks.…”

Section: Introductionmentioning

confidence: 99%

Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications

Campolo

Genovese

Molinaro

2021

JSAN

View full text Add to dashboard Cite

Several Internet of Things (IoT) applications are booming which rely on advanced artificial intelligence (AI) and, in particular, machine learning (ML) algorithms to assist the users and make decisions on their behalf in a large variety of contexts, such as smart homes, smart cities, smart factories. Although the traditional approach is to deploy such compute-intensive algorithms into the centralized cloud, the recent proliferation of low-cost, AI-powered microcontrollers and consumer devices paves the way for having the intelligence pervasively spread along the cloud-to-things continuum. The take off of such a promising vision may be hurdled by the resource constraints of IoT devices and by the heterogeneity of (mostly proprietary) AI-embedded software and hardware platforms. In this paper, we propose a solution for the AI distributed deployment at the deep edge, which lays its foundation in the IoT virtualization concept. We design a virtualization layer hosted at the network edge that is in charge of the semantic description of AI-embedded IoT devices, and, hence, it can expose as well as augment their cognitive capabilities in order to feed intelligent IoT applications. The proposal has been mainly devised with the twofold aim of (i) relieving the pressure on constrained devices that are solicited by multiple parties interested in accessing their generated data and inference, and (ii) and targeting interoperability among AI-powered platforms. A Proof-of-Concept (PoC) is provided to showcase the viability and advantages of the proposed solution.

show abstract

TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities

Cited by 221 publications

References 29 publications

An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

An Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications

The synergy of complex event processing and tiny machine learning in industrial IoT

Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications

Contact Info

Product

Resources

About