Cited by 296IoT and Edge/Fog ComputingInternet of Things and AIIoT Networks and Protocols

The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.

TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities

Sanchez-Iborra, Ramon, Skarmeta, Antonio F.·2020·IEEE Circuits and Systems Magazine

DOI 10.1109/mcas.2020.3005467

Open this paper in CoChat — free account

Abstract

The TinyML paradigm proposes to integrate Machine Learning (ML)-based mechanisms within small objects powered by Microcontroller Units (MCUs). This paves the way for the development of novel applications and services that do not need the omnipresent processing support from the cloud, which is power consuming and involves data security and privacy risks. In this work, a comprehensive review of the novel TinyML ecosystem is provided. The related challenges and opportunities are identified and the potential services that will be enabled by the development of truly smart frugal objects are discussed. As a main contribution of this paper, a detailed survey of the available TinyML frameworks for integrating ML algorithms within MCUs is provided. Besides, aiming at illustrating the given discussion, a real case study is presented. Concretely, we propose a multi-Radio Access Network (RAT) architecture for smart frugal objects. The issue of selecting the most adequate communication interface for sending sporadic messages considering both the status of the device and the characteristics of the data to be sent is addressed. To this end, several TinyML frameworks are evaluated and the performances of a number of ML algorithms embedded in an Arduino Uno board are analyzed. The attained results reveal the validity of the TinyML approach, which successfully enables the integration of techniques such as Neural Networks (NNs), Support Vector Machine (SVM), decision trees, or Random Forest (RF) in frugal objects with constrained hardware resources. The outcomes also show promising results in terms of algorithm's accuracy and computation performance.

Integrity signals

Registry

Crossref · 10.1109/mcas.2020.3005467

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Multimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018
The future of industrial communication: Automation networks in the Era of the internet of things and industry 4.0
Wollschlaeger, M., Sauter, T., & Jasperneite, J. (2017) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2017.2649104 · Cited by 1,726
Mobile edge computing, Fog et al.: A survey and analysis of security threats and challenges
Roman, R., Lopez, J., & Mambo, M. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2016.11.009 · Cited by 1,338
WEKA: a machine learning workbench
Holmes, G., Donkin, A., & Witten, I. H. (2002) · Australian and New Zealand Intelligent Information Systems Conference (ANZIIS) · doi:10.1109/anziis.1994.396988 · Cited by 939
Terminology for Constrained-Node Networks
Bormann, C., Ersue, M., & Keränen, A. (2014) · doi:10.17487/rfc7228 · Cited by 681
Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues
Sun, Y., Peng, M., Zhou, Y., Huang, Y., & Mao, S. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2924243 · Cited by 678
Internet-of-things-based smart environments: state of the art, taxonomy, and open research challenges
Ahmed, E., Yaqoob, I., Gani, A., Imran, M. A., & Guizani, M. (2016) · IEEE Wireless Communications · doi:10.1109/mwc.2016.7721736 · Cited by 448
Internet of Things Platform for Smart Farming: Experiences and Lessons Learnt
Jayaraman, P. P., Yavari, A., Georgakopoulos, D., Morshed, A., & Zaslavsky, A. (2016) · Sensors · doi:10.3390/s16111884 · Cited by 440
The Power of Models: Modeling Power Consumption for IoT Devices
Martinez, B., Montón, M., Vilajosana, I., & Prades, J. D. (2015) · IEEE Sensors Journal · doi:10.1109/jsen.2015.2445094 · Cited by 324

Flagged first, then by citations

Show all 36 references

Research works printed but not linked: 29

2020, Darknet Convolutional Neural Networks
2020, The Microsoft Cognitive Toolkit
2020, Scikit-Learn
2020, TensorFlow™
2020, Embedded Learning Library
2020, TinyGo
2020, TensorFlow Lite
2020, PyTorch
2020, Teensyduino
2020, MBED Platform
2020, Fast Artificial Neural Network Library (FANN)
columbus, 2018, 10 Charts that will change your perspective of big data’s growth
2020, Keras
2020, Caffe
2020, Linaro
2020, TinyMLgen
2020, uTensor
2020, Open neural network exchange
macgillivray, 2019, Internet of Things Spending trends and outlook
doyu, 2019, TinyML as a Service and the challenges of machine learning at the edge
2020, Weka-porter
2020, MicroML
2020, NanoEdge AI Studio
2020, m2cgen
morawiec, 2020, sklearn-porter
2020, Cmsis-nn
2020, Arm NN
2020, AIfES
2020, STM32Cube AI

Sorted by citations

Items 101–200 of 296

A Review on Resource-Constrained Embedded Vision Systems-Based Tiny Machine Learning for Robotic Applications
Beltrán-Escobar, M., Alarcón, T. E., Morales, J. Y. R., López, S., Ortíz-Torres, G., & Sorcia‐Vázquez, F. D. J. (2024) · Algorithms · doi:10.3390/a17110476 · Cited by 18
A Self-Powered Sensing System with Embedded TinyML for Anomaly Detection
Chen, Z., Gao, Y., & Liang, J. (2023) · IEEE International Conference on Industrial Electronics for Sustainable Energy Systems (IESES) · doi:10.1109/ieses53571.2023.10253705 · Cited by 18
Combinative model compression approach for enhancing 1D CNN efficiency for EIT-based Hand Gesture Recognition on IoT edge devices
Mnif, M., Sahnoun, S., Saad, Y. B., Fakhfakh, A., & Kanoun, O. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101403 · Cited by 18
Auritus
Saha, S. S., Sandha, S. S., Pei, S., Jain, V., Wang, Z., Li, Y., Sarker, A., & Srivastava, M. B. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3534586 · Cited by 17
“We achieve this optimization through tight integration of state-of-the-art (SOTA) advances in TinyML and NAS [78, 85] in the model development and generation stages as shown in Fig.”
Method
Time series analysis for temperature forecasting using TinyML
Alati, M. F., Fortino, G., Morales, J., Cecilia, J. M., & Manzoni, P. (2022) · 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC) · doi:10.1109/ccnc49033.2022.9700573 · Cited by 21
Economic Granularity Interval in Decision Tree Algorithm Standardization from an Open Innovation Perspective: Towards a Platform for Sustainable Matching
Li, T., Ma, L., Liu, Z., & Liang, K. (2020) · Journal of Open Innovation Technology Market and Complexity · doi:10.3390/joitmc6040149 · Cited by 16
“The TinyML paradigm aims to integrate machine learning within microcontroller units (MCUs) [3].”
Method
Assessment of Tiny Machine-Learning Computing Systems Under Neutron-Induced Radiation Effects
Bastos, R. P., Trindade, M. G., Garibotti, R., Gava, J., Reis, R. A. L., & Ost, L. C. (2022) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2022.3176485 · Cited by 16
On the Adoption of Modern Technologies to Fight the COVID-19 Pandemic: A Technical Synthesis of Latest Developments
Majeed, A., & Zhang, X. (2023) · COVID · doi:10.3390/covid3010006 · Cited by 17
The Case for Hierarchical Deep Learning Inference at the Network Edge
Al-Atat, G., Fresa, A., Behera, A. P., Moothedath, V. N., Gross, J., & Champati, J. P. (2023) · doi:10.1145/3597062.3597278 · Cited by 15
“Such deployments are enabled by advancements in hardware and the rapid evolution of model compression techniques [3, 23].”
BackgroundMethodInfluential
LogicWiSARD: Memoryless Synthesis of Weightless Neural Networks
Miranda, I. D. S., Arora, A., Susskind, Z., Villon, L. A. Q., Katopodis, R. F., Dutra, D. L. C., Araujo, L. S. D., Lima, P. M. V., França, F. M. G., John, L. K., et al. (2022) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap54787.2022.00014 · Cited by 15
“These characteristics can hinder the deployment of ML-based IoT solutions, given the resource constraints on edge devices [3]–[5].”
Background
Monocular Depth Perception on Microcontrollers for Edge Applications
Peluso, V., Cipolletta, A., Calimera, A., Poggi, M., Tosi, F., Aleotti, F., & Mattoccia, S. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3077395 · Cited by 17
“…from simple image collectors to intelligent hubs able to infer depth locally, namely with no access to the cloud, thereby ensuring portability even in geographical areas with limited data coverage, and higher quality-of-service (QoS) thanks to more certain latency and higher users privacy [3].”
Background
Towards Seamless IoT Device-Edge-Cloud Continuum:
Taivalsaari, A., Mikkonen, T., & Pautasso, C. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-92231-3_8 · Cited by 14
“Popular generic AI/ML solutions include TinyML [9] which allows the integration of ML capabilities with microcontroller units for analytics applications which require an extremely low power (typically in the mW range and below).”
Background
TinyML for UWB-radar based presence detection
Pavan, M., Caltabiano, A., & Roveri, M. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892925 · Cited by 14
“Currently the research in the field of TinyML for presence detection focused on the analysis of data coming from cameras (formalized as a “visual wake-word detection” problem) or microphones (formalized as a “keyword/sound spotting” problem) [9][10].”
BackgroundMethod
RIOT-ML: toolkit for over-the-air secure updates and performance evaluation of TinyML models
Huang, Z., Zandberg, K., Schleiser, K., & Baccelli, E. (2024) · Annals of Telecommunications · doi:10.1007/s12243-024-01041-5 · Cited by 14
MLino bench: A comprehensive benchmarking tool for evaluating ML models on edge devices
Baciu, V.-E., Stiens, J. H., & da Silva, B. (2024) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2024.103262 · Cited by 14
Is Tiny Deep Learning the New Deep Learning?
Roveri, M. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-19-3391-2_2 · Cited by 14
AutoML for On-Sensor Tiny Machine Learning
Chowdhary, M., Lilienthal, D., Saha, S. S., & Palle, K. C. (2023) · IEEE Sensors Letters · doi:10.1109/lsens.2023.3327914 · Cited by 14
“Several no-code automatic machine learning (AutoML) [6], [7], [8] and NAS [9], [10], [11], [12], [13], [14], [15] frameworks are offeredformicrocontrollers.”
Smart and Fault-Tolerant Multisensor Fusion Model for UCM Methane Hazard Monitoring Based on Belief Divergence Backed DS Filter and Hybrid CNN-LSTM Classifier
Sharma, M., & Maity, T. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3295823 · Cited by 13
“Since the ML algorithms are directly running onto the microcontrollers, the data security, or privacy issues are almost negligible in this case [25], [26].”
Machine learning-powered traffic processing in commodity hardware with eBPF
Gallego-Madrid, J., Bru-Santa, I., Ruiz-Rodenas, A., Sanchez‐Iborra, R., & Skármeta, A. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110295 · Cited by 13
Self-citation
TinyML Applications, Research Challenges, and Future Research Directions
Oufettoul, H., Chaibi, R., & Motahhir, S. (2024) · Learning and Technology Conference (L&T) · doi:10.1109/lt60077.2024.10469633 · Cited by 14
“…energy-efﬁcient devices, the amalgamation of machine learning and limited appliances has the potential to exert a substantial impact on the current landscape of IoT applications, particularly in sectors like healthcare (eHealth), intelligent agriculture, manufacturing, and smart homes [1], [2].”
Background
TinyML applications and use cases for healthcare
Bhamare, M., Kulkarni, P., Rane, R., Bobde, S., & Patankar, R. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-322202-3.00019-1 · Cited by 13
Empowering stroke recovery with upper limb rehabilitation monitoring using TinyML based heterogeneous classifiers
Xie, J., Wu, Q., Dey, N., Shi, F., Sherratt, R. S., & Kuang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-01710-y · Cited by 14
“In essence, TinyML can address the challenges associated with cloud-based solutions, such as potential privacy infringement risks, response latency, additional network load, and significant power consumption 54 , and synergizes with algorithms capable of executing intricate tasks.”
Frugal Heart Rate Correction Method for Scalable Health and Safety Monitoring in Construction Sites
Sowiński, P., Rachwał, K., Danilenka, A., Bogacka, K., Kobus, M., Dabrowska, A. K., Paszkiewicz, A., Bolanowski, M., Ganzha, M., & Paprzycki, M. (2023) · Sensors · doi:10.3390/s23146464 · Cited by 13
“In recent years, the term “frugality” has been very influential in machine learning research, due to the popularization of paradigms such as TinyML [52], which strive to adapt machine learning to edge and IoT environments.”
Background
Getting the Best Out of Both Worlds: Algorithms for Hierarchical Inference at the Edge
Moothedath, V. N., Champati, J. P., & Gross, J. (2024) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2024.3366501 · Cited by 15
“On the one hand, there is signiﬁcant research by the tinyML community for building small-size DNNs that can be embedded on micro-controllers and also in designing efﬁcient embedded hardware accelerators [5].”
Background
Tiny Machine Learning (TinyML): Research trends and future application opportunities
Han, H., Trimi, S., & Lee, S. M. (2026) · Array · doi:10.1016/j.array.2025.100674 · Cited by 12
Sleep Apnea Detection System Using Machine Learning on Resource-Constrained Devices
Mallick, S., Gawali, S. K., Onime, C., & Goveas, N. (2023) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon53073.2023.10131117 · Cited by 12
“The interpreter executes the code generated by the converter on the devices [16].”
Method
TinyML-Based Fall Detection for Connected Personal Mobility Vehicles
Sanchez‐Iborra, R., Bernal-Escobedo, L., Santa, J., & Skármeta, A. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.022610 · Cited by 12
“This leads to energy saving in communications and a reduction in application latency [17].”
BackgroundSelf-citation
A Dataset and TinyML Model for Coarse Age Classification Based on Voice Commands
Kadir, A. D. I. A., Al-Haiqi, A., & Din, N. M. (2021) · IEEE Malaysia International Conference on Communications (MICC) · doi:10.1109/micc53484.2021.9642091 · Cited by 12
Online Processing of Vehicular Data on the Edge Through an Unsupervised TinyML Regression Technique
de Andrade, P. H. M., da Silva, I. M. D., Diniz, M., Flores, T. K. S., Costa, D. G., & Soares, E. A. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3591356 · Cited by 14
Mechanical Anomaly Detection on an Embedded Microcontroller
Lord, M., & Kaplan, A. (2021) · 2021 International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci54926.2021.00159 · Cited by 13
“This vastly reduces the overall communication, and addresses the aforementioned bandwidth, energy, and security concerns [3].”
Background
Advances for Dysphagia in the Digital Age: Integrative Imaging and Wearable Technologies
Malandraki, G. A. (2023) · Folia Phoniatrica et Logopaedica · doi:10.1159/000531265 · Cited by 11
Intelligent inspection probe for monitoring bark beetle activities using embedded IoT real-time object detection
Novák, M., Doležal, P., Budík, O., Ptáček, L., Geyer, J., Davídková, M., & Prokýšek, M. (2024) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2024.101637 · Cited by 11
iBUG: AI Enabled IoT Sensing Platform for Real-time Environmental Monitoring
Yousuf, M. F., Siddique, T., & Mahmud, M. S. (2022) · IEEE Microelectronics Design & Test Symposium (MDTS) · doi:10.1109/mdts54894.2022.9826935 · Cited by 11
TinyML-based approach for Remaining Useful Life Prediction of Turbofan Engines
Athanasakis, G., Filios, G., Katsidimas, I., Nikoletseas, S., & Panagiotou, S. H. (2022) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa52439.2022.9921629 · Cited by 10
“TinyML, as a subset of embedded machine learning and edge AI, brings several benefits over cloud AI characteristics, that constitute significant barriers for trusting and deploying, in real time, AI solutions in the Industrial Internet of Things (IIoT) [10], [6], [11].”
Background
Conception and Design of WSN Sensor Nodes Based on Machine Learning, Embedded Systems and IoT Approaches for Pollutant Detection in Aquatic Environments
da Silva, Y. F., Freire, R. C. S., & Neto, J. V. D. F. (2023) · IEEE Access · doi:10.1109/access.2023.3325760 · Cited by 11
“Significant efforts are being made to embed machine learning algorithms in less complex devices as these methods evolve [25], [26].”
Background
Industrial Visual Inspection with TinyML for High-Performance Quality Control
Albanese, A., & Brunelli, D. (2023) · IEEE Instrumentation & Measurement Magazine · doi:10.1109/mim.2023.10292593 · Cited by 10
TinyML for ECG Biometrics on Resource Constrained Devices
Thota, Y. R., & Nikoubin, T. (2024) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi61997.2024.00100 · Cited by 10
“Along with the increasing trend for the artificial intelligence of things (AIoT), TinyML has been considered as an important paradigm [5].”
Background
Analysis of Using Machine Learning Techniques for Estimating Solar Panel Performance in Edge Sensor Devices
Dobrilović, D., Pekez, J., Ognjenović, V., & Desnica, E. (2024) · Applied Sciences · doi:10.3390/app14031296 · Cited by 10
Toward Data-Adaptable TinyML using Model Partial Replacement for Resource Frugal Edge Device
Kwon, J., & Park, D. (2021) · The International Conference on High Performance Computing in Asia-Pacific Region · doi:10.1145/3432261.3439865 · Cited by 10
Probabilistic Caching Strategy and TinyML-Based Trajectory Planning in UAV-Assisted Cellular IoT System
Gao, X., Wang, X., & Qian, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3360444 · Cited by 9
“Other application areas include intelligent healthcare or wearable devices, wireless communication access, and so on [8].”
Background
TinyML network applications for smart cities
Ahmed, Z. E., Hashim, A. H. A., Saeed, R. A., & Saeed, M. M. A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-322202-3.00023-3 · Cited by 9
EdgeMark: An automation and benchmarking system for embedded artificial intelligence tools
Hasanpour, M. A., Kirkegaard, M., & Fafoutis, X. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103488 · Cited by 9
Enabling Efficient Intermittent Computing on Brand New Microcontrollers via Tracking Programmable Voltage Thresholds
Akhunov, K., Yıldız, E., & Yıldırım, K. S. (2023) · International Workshop on Energy Harvesting & Energy-Neutral Sensing Systems (ENSsys) · doi:10.1145/3628353.3628547 · Cited by 9
“The low-power MCU market is growing with the boosting effect of TinyML [33, 38], introducing several brand-new MCUs [2, 10, 14, 16] to support low-power intelligence on the edge.”
Background
Implementation of Smart Security System in Agriculture fields Using Embedded Machine Learning
Viswanatha, V., Ramachandra, A. C., Hegde, P. T., Reddy, M. V., Hegde, V., & Sabhahit, V. (2023) · International Conference on Applied Intelligence and Sustainable Computing (ICAISC) · doi:10.1109/icaisc58445.2023.10200240 · Cited by 9
MicroFlow: An Efficient Rust-Based Inference Engine for TinyML
Carnelos, M., Pasti, F., & Bellotto, N. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101498 · Cited by 8
Empowering IoT security: deploying TinyML ensemble techniques for cyberattack detection
Hamdouchi, A., & Idri, A. (2025) · Scientific African · doi:10.1016/j.sciaf.2025.e02809 · Cited by 8
TinySV: Speaker Verification in TinyML with On-device Learning
Pavan, M., Mombelli, G., Sinacori, F., & Roveri, M. (2024) · International Conference on AI-ML Systems (AIMLSystems) · doi:10.1145/3703412.3703415 · Cited by 8
“Most of the solutions present in this field focus on the design of approximated machine and deep learning solutions [6], [14].”
Shannon Strikes Again! Entropy-based Pruning in Deep Neural Networks for Transfer Learning under Extreme Memory and Computation Budgets
Spadaro, G., Renzulli, R., Bragagnolo, A., Giraldo, J. H., Fiandrotti, A., Grangetto, M., & Tartaglione, E. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00165 · Cited by 10
“As TinyML aims to run machine learning algorithms on resource-constrained devices such as micro-controllers, wearables, and Internet of Things (IoT) devices, these platforms often have limited memory capacities [18].”
Background
Study of the Impact of Data Compression on the Energy Consumption Required for Data Transmission in a Microcontroller-Based System
Piątkowski, D., Puślecki, T., & Walkowiak, K. M. (2023) · Sensors · doi:10.3390/s24010224 · Cited by 7
Evaluating the performance of TinyML singular and ensemble techniques for intrusion detection in IoT networks
Hamdouchi, A., & Idri, A. (2025) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2025.105172 · Cited by 9
Low-cost and non-intrusive human digital twin component for task and navigation tracking through pose estimation
Costa, D., Pereira, D. L., Brochado, Â. F., & Rocha, E. M. (2025) · CIRP journal of manufacturing science and technology · doi:10.1016/j.cirpj.2025.05.012 · Cited by 7
Exploring the Boundaries of On-Device Inference: When Tiny Falls Short, Go Hierarchical
Behera, A. P., Daubaris, P., Bravo, I., Gallego, J., Morabito, R., Widmer, J., & Champati, J. P. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3583477 · Cited by 7
“On-Device Inference: As discussed in Section I, considerable effort has been devoted to designing compact DL models suitable for deployment on end devices [4], [25], [26], [27].”
U-TOE: Universal TinyML On-Board Evaluation Toolkit for Low-Power IoT
Huang, Z., Zandberg, K., Schleiser, K., & Baccelli, E. (2023) · IFIP/IEEE International Conference on Performance Evaluation and Modeling in Wired and Wireless Networks (PEMWN) · doi:10.23919/pemwn58813.2023.10304946 · Cited by 7
“Recent work from the TinyML [13, 11] community forays into optimizing models to fit tinier resource budgets (and”
Method
TinyML for 5G networks
Saeed, M. M. A., Saeed, R. A., & Ahmed, Z. E. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-322202-3.00014-2 · Cited by 7
Experience with the Implementation of Machine Learning on ESP32-Based Edge Devices
Dobrilović, D. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-72483-1_11 · Cited by 7
Machine learning-based radio access technology selection in the Internet of moving things
Sanchez‐Iborra, R., Bernal-Escobedo, L., & Santa, J. (2021) · China Communications · doi:10.23919/jcc.2021.07.002 · Cited by 7
Self-citation
TinyML-Based Concept System Used to Analyze Whether the Face Mask Is Worn Properly in Battery-Operated Conditions
Piątkowski, D., & Walkowiak, K. M. (2022) · Applied Sciences · doi:10.3390/app12010484 · Cited by 7
MobileNets Can Be Lossily Compressed: Neural Network Compression for Embedded Accelerators
Lim, S.-M., & Jun, S.-W. (2022) · Electronics · doi:10.3390/electronics11060858 · Cited by 7
Evaluating the practical limitations of TinyML: an experimental approach
Delnevo, G., Prandi, C., Mirri, S., & Manzoni, P. (2021) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps52748.2021.9682101 · Cited by 7
“TinyML presents unique opportunities also for frugal objects [7], which have penetrated our daily lives thanks to the rapid emergence of the IoT (Internet of Things).”
Background
A Practical View on Training Neural Networks in the Edge
Rüb, M., & Sikora, A. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2022.06.045 · Cited by 9
Implementation of a sensor node for monitoring and classification of physiological signals in an edge computing system
Yauri, R., Nieto, A. C., Espino, R., & Carrillo, S. G. G. (2022) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v28.i1.pp98-105 · Cited by 7
“Then a wireless transmission stage and power control is used with a ESP8266 microcontroller [14], [15] (Figure 1).”
Regret Bounds for Online Learning for Hierarchical Inference
Al-Atat, G., Datta, P., Moharir, S., & Champati, J. P. (2024) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3641512.3686392 · Cited by 7
Embedded Machine Learning: Towards a Low-Cost Intelligent IoT edge
Shumba, A. T., Montanaro, T., Sergi, I., Fachechi, L., Vittorio, M. D., & Patrono, L. (2022) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech55088.2022.9854248 · Cited by 6
“…accessing and transferring data to the cloud comes at a high cost, imposes a huge burden on the cloud infrastructure resulting in significant latency due to factors like bandwidth limitations, and introduces privacy issues due to the vulnerable nature of the communication networks [3], [16].”
BackgroundMethod
A Tiny CNN for Embedded Electronic Skin Systems
Sakr, F., Younes, H., Doyle, J. C., Bellotti, F., Gloria, A. D., & Berta, R. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-16281-7_53 · Cited by 6
Automatic Generation of Resource and Accuracy Configurable Processing Elements
León-Vega, L. G., Salazar-Villalobos, E., Rodriguez-Figueroa, A., & Godinez, J. C. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3594540 · Cited by 6
“TinyML involves several frameworks from academia and industry to create smaller models capable of running on several devices.”
BackgroundMethodInfluential
On-Sensor Online Learning and Classification Under 8 KB Memory
Chowdhary, M., & Saha, S. S. (2023) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion52260.2023.10224228 · Cited by 6
“To enable artificial intelligence (AI) for time-critical and remote applications, tiny machine learning (tinyML) provides hardware and software paradigms that enable always-on, real-time, low-cost, and ultra-low-power inference on microcontrollers [23]–[26].”
Background
Smart Machine Learning-based IoT Health and Cough Monitoring System
Pang, W. L., Chung, G. C., Chan, K., Ee, L. I., Roslee, M., Fitrey, E., Sim, Y. W., & Prasetio, M. D. (2023) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.13.5.19024 · Cited by 6
Evaluation of a Machine Learning Algorithm to Classify Ultrasonic Transducer Misalignment and Deployment Using TinyML
Brennan, D., & Galvin, P. (2024) · Sensors · doi:10.3390/s24020560 · Cited by 6
“…were considered, the output layer was a vector of dimension 8 × 1 (i.e., one node representing each class), with a softmax activation function determining which output node was activated to classify the input signal. nodes per layer were hyper-parameters optimised during the training process.”
MethodInfluential
Symbolic knowledge injection meets intelligent agents: QoS metrics and experiments
Agiollo, A., Rafanelli, A., Magnini, M., Ciatto, G., & Omicini, A. (2023) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-023-09609-6 · Cited by 18
“This is why recent research efforts in the AI field are focussing on time-sensitive predictors.”
Fall Detection Systems Supported by TinyML and Accelerometer Sensors: An Approach for Ensuring the Safety and Quality of Life of the Elderly
Durgun, Y. (2023) · International Scientific and Vocational Studies Journal · doi:10.47897/bilmes.1299289 · Cited by 6
“Örneğin, kullanıcının hareketlerini ve pozisyonunu izleyen sensörler kullanarak düşme riskini takip edebilmektedir [8-9].”
An On-Board Executable Pareto-Based Iterated Local Search Algorithm for Embedded Multi-Core Processor Task Scheduling
Zhao, Q., Zhang, L., Pan, Q., Cui, K., Zhao, M., Tian, F., & Hu, B. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3603699 · Cited by 5
“Tiny machine learning (TinyML) [43] represents an exciting novel frontier in the ﬁeld of machine learning that enables the deployment of machine learning in embedded devices, enabling ubiquitous intelligence.”
Edge-compatible SOH estimation for Li-ion batteries via hybrid knowledge distillation and model compression
Kim, T., Seo, Y., & Barde, S. (2025) · Journal of Energy Storage · doi:10.1016/j.est.2025.118275 · Cited by 7
IIoT-TinyDNN: A Lightweight Intrusion Detection System for Edge-Based IIoT Security
A.Abualhassan, A., Fadol, Y., Gismalla, M. S. M., & Hamdan, M. (2025) · IEEE Conference on Standards for Communications and Networking · doi:10.1109/cscn67557.2025.11230733 · Cited by 5
Implementing TinyML in Internet of Things devices: A systematic literature review
Pino, A. F. S., Pizarro, D. S. M., Ruiz, P. H., Agredo-Delgado, V., Collazos, C. A., & Moreira, F. (2026) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2026.101065 · Cited by 5
REST and EDA architectures in IoT actuation
Herrero, R. (2023) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.05.002 · Cited by 5
Prediction of Remaining Useful Life and Cell Temperature for Li-ion Batteries Using TinyML
Weng, Y., Guan, W., & Ababei, C. (2024) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas60917.2024.10658694 · Cited by 5
“However, in many practical situations [12], we actually want such models to be implemented on IoT devices, which are typically built using microcontrollers, which are resource constrained (i.e., memory capacities in the order of 250KB only).”
Background
Fast Resource Estimation of FPGA-Based MLP Accelerators for TinyML Applications
Kokkinis, A., & Siozios, K. (2025) · Electronics · doi:10.3390/electronics14020247 · Cited by 5
Hybrid Solution Through Systematic Electrical Impedance Tomography Data Reduction and CNN Compression for Efficient Hand Gesture Recognition on Resource-Constrained IoT Devices
Sahnoun, S., Mnif, M., Ghoul, B., Jemal, M., Fakhfakh, A., & Kanoun, O. (2025) · Future Internet · doi:10.3390/fi17020089 · Cited by 5
Engineering a multi model fallback system for edge devices
Kadve, G., Chowdhury, A., Singh, V. K., & Pal, A. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.105165 · Cited by 5
Position Paper: Low-Cost Solutions for Home-Based Healthcare
Yamanoor, S., & Yamanoor, N. S. (2021) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets51098.2021.9352859 · Cited by 5
“7) In relation to machine learning and edge computing, open software tools such as TensorFlow [25] and TinyML [26] must be selected for solution development.”
Construction of Garden Landscape Design System Based on Multimodal Intelligent Computing and Deep Neural Network
Yu, X., Yu, H., & Liu, C. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/8332180 · Cited by 5
“Such [8–11].”
Deep and Wide Tiny Machine Learning
Disabato, S. (2022) · SpringerBriefs in applied sciences and technology · doi:10.1007/978-3-031-15374-7_7 · Cited by 5
Anomaly Detection in Multi-Wavelength Photoplethysmography Using Lightweight Machine Learning Algorithms
Baciu, V.-E., Cause, J. L., Morillo, Á. S., Naranjo, J. C. G., Stiens, J. H., & da Silva, B. (2023) · Sensors · doi:10.3390/s23156947 · Cited by 5
“In [25], the authors present a vast number of frameworks and ML algorithms that are state-of-the-art and can be easily deployed on wearable devices with the help of opensource frameworks.”
Background
Resource-Constrained Device Characterization for Detecting Sleep Apnea Using Machine Learning
Mallick, S., Ruparel, P., Gawali, S. K., & Goveas, N. (2023) · International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets58706.2023.10216211 · Cited by 5
“The interpreter executes the code generated by the converter on these devices [22].”
Method
A TinyML-based system for prosthetic control
Wu, H., & Nazarpour, K. (2023) · IEEE International Conference on Information, Communication and Networks (ICICN) · doi:10.1109/icicn59530.2023.10392863 · Cited by 5
“The most common TinyML approaches are the conversion of trained models and adapting them to the restrictions of MCUs [8].”
Method
Towards Large-Scale IoT Deployments in Smart Cities: Requirements and Challenges
Motlagh, N. H., Zaidan, M. A., Morabito, R., Nurmi, P., & Tarkoma, S. (2023) · Springer eBooks · doi:10.1007/978-3-031-50514-0_6 · Cited by 6
Development of Speech Command Control Based TinyML System for Post-Stroke Dysarthria Therapy Device
Riyanta, B., Irianta, H. A., & Kamiel, B. P. (2023) · Journal of Robotics and Control (JRC) · doi:10.18196/jrc.v4i4.15918 · Cited by 4
AoI-Aware Retained Message Policy in MQTT-Based IoT Networks
Kim, Y., & Kyung, Y. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3465025 · Cited by 5
CNN-based prediction of multi-variables for lithium-ion batteries optimized with TinyML and deployed on edge devices
Weng, Y., Guan, W., & Ababei, C. (2025) · Journal of Energy Storage · doi:10.1016/j.est.2025.119508 · Cited by 4
Distributed TinyML on Resource-Constrained IoT Sensor Networks
Yuan, Z., & Law, K. L. E. (2024) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot62078.2024.10811277 · Cited by 4
“Thus, the TinyML ( tiny machine learning ) [1] concept has recently been raised on deploying machine learning algorithms on microcontrollers or devices with limited resources.”
SISTINE 2.0: Sensorized Socks for Postural Telemonitoring
Lucangeli, L., D’Angelantonio, E., Camomilla, V., & Pallotti, A. (2022) · IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT) · doi:10.1109/metroind4.0iot54413.2022.9831630 · Cited by 4
To Personalize or Not To Personalize? Soft Personalization and the Ethics of ML for Health
Falcetta, A., Pavan, M., Canali, S., Schiaffonati, V., & Roveri, M. (2023) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa60987.2023.10302472 · Cited by 4
“…in the field of ML lead to the possibility of executing ML models directly on-device (for instance Health-related Internet of Things or wearable devices, leveraging TinyML [8]) or on encrypted data (for instance with Homomorphic Encryption (HE) [9]), thus applying privacy-preserving approaches.”
Background
Smart Minion: A Low-cost Serverless Multimodal Access Control System Based on Face Recognition and Gesture Recognition
Chen, Z., Gao, Y., & Liang, J. (2023) · International Conference on Artificial Intelligence of Things and Systems (AIoTSys) · doi:10.1109/aiotsys58602.2023.00042 · Cited by 4
“TinyML, a booming branch of state-of-the-art ML techniques, enables the low-cost MCU to run on-device ML models at a milliwatt-level power consumption without real-time support of large servers [10].”
Background
Voice Activated Edge Devices Using Tiny Machine Learning Enabled Microcontroller
Uddin, M. R., Asaduzzaman, A. S., Le, K., & Medarametla, R. R. (2024) · IEEE Green Technologies Conference (GreenTech) · doi:10.1109/greentech58819.2024.10520459 · Cited by 4
“The comprehensive review done by Iborra et al. [12] explores the TinyML ecosystem, identifying challenges, opportunities, and potential services offered by smart frugal objects.”
Background
eBPF and XDP Technologies as Enablers for Ultra-Fast and Programmable Next-Gen Network Infrastructures
Gallego-Madrid, J., Sanchez‐Iborra, R., & Skármeta, A. (2024) · Studies in big data · doi:10.1007/978-981-97-2644-8_13 · Cited by 4
Self-citation
A TinyML Motion-Based Embedded Cough Detection System
Diab, M. S., & Rodriguez–Villegas, E. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10782961 · Cited by 4
Design and Development of A-vent: A Low-Cost Ventilator with Cost-Effective Mobile Cloud Caching and Embedded Machine Learning
Cabacungan, P. M., Oppus, C. M., Cabacungan, N. G., Mamaradlo, J. P. A., Santiago, P. R. A., Mercado, N. A. M., Faustino, E. V. S., & Tangonan, G. L. (2021) · IEEE Region 10 Symposium (TENSYMP) · doi:10.1109/tensymp52854.2021.9550920 · Cited by 4
“These big data sets have many variables, which necessitates a lot of computational resources to process [16].”
BackgroundMethod
Who is wearing me? TinyDL‐based user recognition in constrained personal devices
Sanchez‐Iborra, R., & Skármeta, A. (2021) · IET Computers & Digital Techniques · doi:10.1049/cdt2.12035 · Cited by 4
Self-citation
Phone of Things (PoT) : Empowering IoT Systems Through the Ubiquitous Telephone Network Infrastructure and Voice Commands
Khalil, H., & Elgazzar, K. (2021) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot51360.2021.9595561 · Cited by 4
Securing the Hyperconnected Healthcare Ecosystem
Sanchez‐Iborra, R., & Skármeta, A. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-90618-4_22 · Cited by 4
Self-citation

Authors: Sanchez-Iborra, R., & Skarmeta, A. F.
Venue: IEEE Circuits and Systems Magazine
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Published: 2020
Volume: 20
Issue: 3
Pages: 4-18
ISSN: 0163-6812 (ISSN-L)
1531-636X
1558-0830
DOI: 10.1109/mcas.2020.3005467
OpenAlex: W3067862503
Cited by: 295
References: 36
Citations by year: 2026: 26 · 2025: 38 · 2024: 57 · 2023: 67 · 2022: 63 · 2021: 40 · 2020: 4
FWCI: 20.44
Type: journal article
Language: en
Open access: closed
Licence: ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html (vor)
doi.org/10.15223/policy-029 (stm-asf)
doi.org/10.15223/policy-037 (stm-asf)
Locations: IEEE Circuits and Systems Magazine (publishedVersion)
Funders: European Commission IoTCrawler (779852)
European Commission CyberSec4Europe (830929)
European Commission Fed4IoT (814918)
Spanish Ministry of Science Innovation and Universities - PERSEIDES (TIN2017-86885-R)
Topics: Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
Physical Sciences › Engineering › Electrical and Electronic Engineering › IoT Networks and Protocols
Keywords: TinyML, microcontroller, embedded machine learning, Arduino Uno, artificial neural networks, support vector machine, random forest, decision tree, edge computing

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks