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
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“TinyML processes data locally in microcontroller devices that have low cost and can apply AI locally on the device itself to process the data with high performance [23].”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [23]
In the citing paper
“When the data is transmitted to the cloud, it is prone to transmission errors, cyber-attacks e.g., eavesdropping or man-in-the-middle issues. Thereby, the transmitted data may be compromised or lost.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [23]
In the citing paper
“Since IoT devices that work on MCUs rely on batteries or even energy harvesting, they consume less energy in comparison with powerful processors and Graphics Processing Units (GPUs) that demand a great amount of power.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [23]
Citations
Cites
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
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
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
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
Cited by
Sorted by citations
A review on TinyML: State-of-the-art and prospects
Ray, P. P. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.11.019 · Cited by 460
A Comprehensive Survey on TinyML
Abadade, Y., Temouden, A., Bamoumen, H., Benamar, N., Chtouki, Y., & Hafid, A. S. (2023) · IEEE Access · doi:10.1109/access.2023.3294111 · Cited by 366
TinyML Meets IoT: A Comprehensive Survey
Dutta, L., & Bharali, S. (2021) · Internet of Things · doi:10.1016/j.iot.2021.100461 · Cited by 365
Towards the fully automated monitoring of ecological communities
Besson, M., Alison, J., Bjerge, K., Gorochowski, T. E., Høye, T. T., Jucker, T., Mann, H. M. R., & Clements, C. F. (2022) · Ecology Letters · doi:10.1111/ele.14123 · Cited by 304
“Furthermore, specialised microprocessors and models are beginning to emerge to efficiently run in low power settings (Lou et al., 2020; Sanchez-Iborra & Skarmeta, 2020).”
Machine Learning for Microcontroller-Class Hardware: A Review
Saha, S. S., Sandha, S. S., & Srivastava, M. B. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3210773 · Cited by 300
“While prior surveys [3] [4] [6] [7] present a qualitative review”
BackgroundInfluentialEnergy-Efficient Industrial Internet of Things: Overview and Open Issues
Mao, W., Zhao, Z., Chang, Z., Min, G., & Gao, W. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3067026 · Cited by 231
TinyML for Ultra-Low Power AI and Large Scale IoT Deployments: A Systematic Review
Schizas, N., Karras, A., Karras, C., & Sioutas, S. (2022) · Future Internet · doi:10.3390/fi14120363 · Cited by 255
Alajlan, N. N., & Ibrahim, D. M. (2022) · Micromachines · doi:10.3390/mi13060851 · Cited by 224
“TinyML processes data locally in microcontroller devices that have low cost and can apply AI locally on the device itself to process the data with high performance [23].”
BackgroundIslam, M. M., Nooruddin, S., Karray, F. O., & Muhammad, G. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3228795 · Cited by 209
“Due to advances in TinyML [182], it might be possible to run anomaly detection models in the future in resource-constrained devices [183].”
MethodAn Overview of Machine Learning within Embedded and Mobile Devices–Optimizations and Applications
Ajani, T. S., Imoize, A. L., & Atayero, A. A. A. (2021) · Sensors · doi:10.3390/s21134412 · Cited by 195
“TinyML is a machine learning technique that integrates compressed and optimized machine learning to suit very low-power MCUs [141].”
BackgroundMethodInfluentialTinyOL: TinyML with Online-Learning on Microcontrollers
Ren, H., Anicic, D., & Runkler, T. A. (2021) · 2021 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533927 · Cited by 185
“Remarkable results have been produced recently, such as voice and facial recognition [4] [5].”
BackgroundA Machine Learning-Oriented Survey on Tiny Machine Learning
Capogrosso, L., Cunico, F., Cheng, D. S., Fummi, F., & Cristani, M. (2024) · IEEE Access · doi:10.1109/access.2024.3365349 · Cited by 209
“In [28], the authors analyze the TinyML frameworks for integrating ML algorithms within MCUs and present a real-world case study.”
BackgroundHeydari, S., & Mahmoud, Q. H. (2025) · Sensors · doi:10.3390/s25103191 · Cited by 223
Federated learning for IoT devices: Enhancing TinyML with on-board training
Ficco, M., Guerriero, A., Milite, E., Palmieri, F., Pietrantuono, R., & Russo, S. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102189 · Cited by 156
Intelligence at the Extreme Edge: A Survey on Reformable TinyML
Rajapakse, V., Karunanayake, I., & Ahmed, N. (2023) · ACM Computing Surveys · doi:10.1145/3583683 · Cited by 140
“This cost-effectiveness encourages use cases such as low latency analysis and modeling of sensor signals from sensors in the manufacturing industry, agriculture, e-health, or entertainment [79].”
BackgroundMethodInfluentialEnergy consumption of on-device machine learning models for IoT intrusion detection
Tekin, N., Acar, A., Arış, A., Uluagac, A. S., & Güngör, V. Ç. (2022) · Internet of Things · doi:10.1016/j.iot.2022.100670 · Cited by 141
“Additionally, various open-source TinyML frameworks such as EmbML [21], emlearn [22], and MicroMLGen [23] are proposed in the literature.”
MethodTinyML: Tools, applications, challenges, and future research directions
Kallimani, R., Pai, K., Raghuwanshi, P., Iyer, S., & López, O. L. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16740-9 · Cited by 145
“The study conducted by [33] shows that many of the architectures are available to the public with the exception of Fraunhofer IMS and Cartesiam-developed AlfES and Na-”
TinyML: A Systematic Review and Synthesis of Existing Research
Han, H., & Siebert, J. (2022) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic54071.2022.9722636 · Cited by 117
A Review on the emerging technology of TinyML
Tsoukas, V., Gkogkidis, A., Boumpa, E., & Kakarountas, A. P. (2024) · ACM Computing Surveys · doi:10.1145/3661820 · Cited by 130
“This ML inference engine is an open-source software development kit that fills the difference between current NN frameworks and energy-efficient Arm IP.”
BackgroundMethodInfluentialWearable devices for continuous monitoring of biosignals: Challenges and opportunities
Stuart, T., Hanna, J., & Gutruf, P. (2022) · APL Bioengineering · doi:10.1063/5.0086935 · Cited by 121
“Local computation presents many opportunities in terms of data safety, latency, 155,156 power consumption, 157,158 personalized treatments, and data privacy and security 155,156 [Fig.”
TinyML-Based Classification in an ECG Monitoring Embedded System
Kim, E., Kim, J., Park, J., Ko, H., & Kyung, Y. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.031663 · Cited by 98
“Along with the increasing trend for the artificial intelligence of things (AIoT), TinyML has been considered as an important paradigm [24].”
BackgroundUtilization of mobile edge computing on the Internet of Medical Things: A survey
Awad, A. I., Fouda, M. M., Khashaba, M. M., Mohamed, E. R., & Hosny, K. M. (2022) · ICT Express · doi:10.1016/j.icte.2022.05.006 · Cited by 100
López, O. L. A., Rosabal, O. M., Ruiz-Guirola, D. E., Raghuwanshi, P., Mikhaylov, K., Lovén, L., & Iyer, S. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3323832 · Cited by 113
“By considering situational characteristics, such as the available energy on a device and the size/urgency level of data to be transmitted, a TinyML-based multi-RAT IoT device can intelligently select a particular RAT for transmission at a given time instance [305].”
BackgroundMachine learning-based zero-touch network and service management: a survey
Gallego-Madrid, J., Sanchez‐Iborra, R., Ruiz, P. M., & Skármeta, A. (2021) · Digital Communications and Networks · doi:10.1016/j.dcan.2021.09.001 · Cited by 92
Self-citationTiny Machine Learning for Resource-Constrained Microcontrollers
Immonen, R., & Hämäläinen, T. (2022) · Journal of Sensors · doi:10.1155/2022/7437023 · Cited by 85
“The authors in [61] tested emlearn, sklearn-porter, and MicroMLgen classic ML libraries with an extremely constrained Arduino Uno microcontroller that had only an 8-bit processor, a clock speed of 16MHz, 32 kB of flash memory, and 2 kB of SRAM.”
BackgroundMethodAI on the edge: a comprehensive review
Su, W., Li, L., Liu, F., He, M., & Liang, X. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10141-4 · Cited by 90
“Tiny machine learning (TinyML) (Sanchez-Iborra and Skarmeta 2020; Banbury et al.”
BackgroundA Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks
Ahmadilivani, M. H., Taheri, M., Raik, J., Daneshtalab, M., & Jenihhin, M. (2023) · ACM Computing Surveys · doi:10.1145/3638242 · Cited by 102
“, ARM processors, deploy DNNs mostly for edge processing and Internet of Things (IoT) applications [45][46][47].”
BackgroundDiab, M. S., & Rodriguez–Villegas, E. (2022) · IEEE Access · doi:10.1109/access.2022.3206782 · Cited by 92
“It allows 476 the conversion of floating-point models into fixed point 477 representation compatible for deployment onto Cortex-M 478 MCUs [27].”
MethodA Review of Machine Learning and TinyML in Healthcare
Tsoukas, V., Boumpa, E., Giannakas, G., & Kakarountas, A. (2021) · 25th Pan-Hellenic Conference on Informatics · doi:10.1145/3503823.3503836 · Cited by 79
“Over the last decade, there has been significant research interest in embedded Machine Learning into Microcontrollers (MCUs) [12, 36].”
BackgroundAn Effective Forest Fire Detection Framework Using Heterogeneous Wireless Multimedia Sensor Networks
Kizilkaya, B., Ever, E., Yatbaz, H. Y., & Yazıcı, A. (2022) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3473037 · Cited by 83
“For example, STM32F2 series comes with up to 120 MHz CPU speed, 1 MB of Flash, and up to 128 kB of SRAM [29], whereas Arduino MEGA 2560 supports clock speeds up to 16 MHz, with 256 KB of flash program memory and 8 KB of SRAM [26].”
Asutkar, S., Chalke, C., Shivgan, K., & Tallur, S. G. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119016 · Cited by 71
Intrusion Detection Based on Federated Learning: A Systematic Review
Hernández-Ramos, J. L., Καρόπουλος, Γ., Chatzoglou, E., Kouliaridis, V., Campos, E. M., González-Vidal, A., & Kambourakis, G. (2025) · ACM Computing Surveys · doi:10.1145/3731596 · Cited by 117
A TinyML Soft-Sensor Approach for Low-Cost Detection and Monitoring of Vehicular Emissions
Andrade, P., Silva, I., Silva, M., Flores, T., Cassiano, J., & Costa, D. G. (2022) · Sensors · doi:10.3390/s22103838 · Cited by 66
“Since the employed devices may have low processing power and restricted memory, more complex machine learning techniques may be prohibitive [18,19].”
BackgroundA survey on artificial intelligence for reducing the climate footprint in healthcare
Das, K. P., & Chandra, J. (2022) · Energy Nexus · doi:10.1016/j.nexus.2022.100167 · Cited by 68
IIsy: Hybrid In-Network Classification Using Programmable Switches
Zheng, C., Xiong, Z., Bui, T. T., Kaupmees, S., Bensoussane, R., Bernabeu, A., Vargaftik, S., Ben-Itzhak, Y., & Zilberman, N. (2024) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2024.3364757 · Cited by 107
“The challenges of ML have led researchers to explore new approaches to resource-constrained ML, using devices of limited resources [67], [68]).”
BackgroundOn TinyML and Cybersecurity: Electric Vehicle Charging Infrastructure Use Case
Dehrouyeh, F., Yang, L., Ajaei, F. B., & Shami, A. A. (2024) · IEEE Access · doi:10.1109/access.2024.3437192 · Cited by 57
“• Energy Efficiency: Processing tasks consume significantly lower energy than wireless transmissions [27].”
BackgroundInfluentialIncremental On-Device Tiny Machine Learning
Disabato, S., & Roveri, M. (2020) · International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things (AIChallengeIoT) · doi:10.1145/3417313.3429378 · Cited by 65
“Techniques belonging to this research field are diversified and fragmented but generally fall under the umbrella of Tiny Machine Learning (TML) [4, 29].”
BackgroundTinyML Smart Sensor for Energy Saving in Internet of Things Precision Agriculture platform
Nicolas, C., Naila, B., & Amar, R.-C. (2022) · 2022 Thirteenth International Conference on Ubiquitous and Future Networks (ICUFN) · doi:10.1109/icufn55119.2022.9829675 · Cited by 53
“However, more recent research on embedded AI has shown that the Tiny ML paradigm now allows micro-controller with small computing capabilities to perform AI directly on the device [5].”
BackgroundMazzi, Y., Ben Sassi, H., Gaga, A., & Errahimi, F. (2022) · International Journal of Energy Research · doi:10.1002/er.7713 · Cited by 53
“40 In these later solutions, the data and sensor measurements are sent to the cloud.”
BackgroundEnergy-Efficient Inference on the Edge Exploiting TinyML Capabilities for UAVs
Raza, W., Osman, A., Ferrini, F., & Natale, F. D. (2021) · Drones · doi:10.3390/drones5040127 · Cited by 53
“TFLM is one of the most widely used TinyML frameworks, which is compatible with the well-known ML libraries TensorFlow [9] and Keras [10].”
MethodInfluentialTiny Machine Learning for High Accuracy Product Quality Inspection
Albanese, A., Nardello, M., Fiacco, G., & Brunelli, D. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3225227 · Cited by 53
“This approach improves the application’s responsiveness and efficiency and reduces the amount of data transmitted [5].”
BackgroundTinyML Algorithms for Big Data Management in Large-Scale IoT Systems
Karras, A., Γιάνναρος, Α., Karras, C., Theodorakopoulos, L., Mammassis, C. S., Krimpas, G. A., & Sioutas, S. (2024) · Future Internet · doi:10.3390/fi16020042 · Cited by 58
Federated learning and TinyML on IoT edge devices: Challenges, advances, and future directions
Ramadan, M. N. A., Ali, M. A. H., Khoo, S. Y., & AlKhedher, M. A. (2025) · ICT Express · doi:10.1016/j.icte.2025.06.008 · Cited by 57
Coelho, D., Costa, D., Rocha, E. M., Almeida, D., & Santos, J. P. O. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.01.318 · Cited by 49
Wei, S. J., Riza, D. F. A., & Nugroho, H. (2022) · Journal of Agriculture and Food Research · doi:10.1016/j.jafr.2022.100389 · Cited by 49
Butt, M. A., Qayyum, A., Ali, H. M., Al‐Fuqaha, A., & Qadir, J. (2022) · Computers & Security · doi:10.1016/j.cose.2022.103058 · Cited by 51
Wireless Battery-free and Fully Implantable Organ Interfaces
Bhatia, A., Hanna, J., Stuart, T., Kasper, K. A., Clausen, D. M., & Gutruf, P. (2024) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00425 · Cited by 50
Sawant, S., Patil, S., Thalapil, J., Banerjee, S., & Tallur, S. G. (2022) · Smart Materials and Structures · doi:10.1088/1361-665x/ac5ce3 · Cited by 47
“Additionally, we seek to also explore development of light-weight deep learning models inspired by TinyML framework [48], that could be directly embedded in the FPGA based embedded system presented in this work, to truly design portable smart SHM systems.”
LPWAN and Embedded Machine Learning as Enablers for the Next Generation of Wearable Devices
Sanchez‐Iborra, R. (2021) · Sensors · doi:10.3390/s21155218 · Cited by 46
“Thus, the embedded intelligence will interact with the stored data in order to make smart decisions (TinyML) that may trigger certain actions or contribute to the cooperative development of an FL-based model, among other activities [6].”
BackgroundMethodInfluentialSelf-citationHayajneh, A. M., Alasali, F., Salama, A., & Holderbaum, W. (2024) · IEEE Access · doi:10.1109/access.2024.3354703 · Cited by 45
“Our study builds on this foundation, optimizing these models for TinyML applications in edge computing environments [20], [21].”
MethodAndrade, P., Silva, I., Signoretti, G., Silva, M., Dias, J., Marques, L., & Costa, D. G. (2021) · 2021 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT) · doi:10.1109/metroind4.0iot51437.2021.9488546 · Cited by 47
Coffen, B., & Mahmud, M. S. (2021) · 2020 IEEE International Conference on E-health Networking, Application & Services (HEALTHCOM) · doi:10.1109/healthcom49281.2021.9399005 · Cited by 44
“This framework, which is built on the well known and used Tensorflow (TF) platform, which can be used for many machine learning tasks, such as image and text classification, generative adversarial networks, and time-series forecasting [3].”
MethodIntegrating LPWAN Technologies in the 5G Ecosystem: A Survey on Security Challenges and Solutions
Sánchez-Gómez, J., García-Carrillo, D., Sanchez‐Iborra, R., Hernández-Ramos, J. L., Granjal, J., Marín-Pérez, R., & Zamora, M. Á. (2020) · IEEE Access · doi:10.1109/access.2020.3041057 · Cited by 42
“In fact, some of the identified potential applications are oriented to on-device security operations [128].”
BackgroundSelf-citationTiny Machine Learning for Concept Drift
Disabato, S., & Roveri, M. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3229897 · Cited by 51
“Digital Object Identifier 10.1109/TNNLS.2022.3229897 deep learning solutions are typically characterized by memory and computational demands that rarely match the constraints on memory, computation, and energy characterizing the IoT units and embedded systems [1], [2], [3].”
BackgroundMethodInfluentialSaha, S. S., Sandha, S. S., Garcia, L. A., & Srivastava, M. B. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3534594 · Cited by 41
“Software advances in TinyML include the use of pruning, quantization and model compression, lightweight neural blocks, hardware-aware NAS and the rise of commercial off-the-shelf (COTS) tools [64, 67]”
MethodToward Virtualized Optical-Wireless Heterogeneous Networks
Vujičić, Z., Santos, M. C., Méndez, R., Klaiqi, B., Rodrı́guez, J., Gelabert, X., Rahman, M. A., & Gaudino, R. (2024) · IEEE Access · doi:10.1109/access.2024.3417358 · Cited by 40
TinyML Empowered Transfer Learning on the Edge
Hayajneh, A. M., Hafeez, M., Zaidi, S. A. R., & McLernon, D. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3373177 · Cited by 43
“Transitioning to TinyML : TinyML technologies have brought a fresh perspective to edge computing, with a particular focus on HAR [23], [24], [25].”
BackgroundSugianto, N., Tjondronegoro, D., Stockdale, R., & Yuwono, E. I. (2021) · Information Technology and People · doi:10.1108/itp-07-2020-0534 · Cited by 39
A Battery-Free Long-Range Wireless Smart Camera for Face Detection
Giordano, M., Mayer, P., & Magno, M. (2020) · Proceedings of the 8th International Workshop on Energy Harvesting and Energy-Neutral Sensing Systems · doi:10.1145/3417308.3430273 · Cited by 38
“A class of ML that is becoming more and more attractive and challenging for ML is the edge ML or tiny machine learning [19], where ML algorithms are compressed to run in resource-constrained microcontrollers [21].”
BackgroundA review of on-device machine learning for IoT: An energy perspective
Tekin, N., Arış, A., Acar, A., Uluagac, A. S., & Güngör, V. Ç. (2023) · Ad Hoc Networks · doi:10.1016/j.adhoc.2023.103348 · Cited by 37
Ding, L., Zhang, C., Yue, Y., Yao, C., Li, Z., Hu, Y., Yang, B., Ma, W., Li, Q., Yu, L., et al. (2025) · Sensors · doi:10.3390/s25144515 · Cited by 37
A TinyMLaaS Ecosystem for Machine Learning in IoT: Overview and Research Challenges
Doyu, H., Morabito, R., & Brachmann, M. (2021) · International Symposium on VLSI Design, Automation and Test · doi:10.1109/vlsi-dat52063.2021.9427352 · Cited by 45
“Combining ML and constrained devices is envisioned to have a great impact on the current IoT application landscape, in areas such as e-Health, smart agriculture and farming, production, and smart home [6] by involving tiny and energy-efficient always-on devices [7].”
BackgroundInfluentialHardware/Software Co-Design for TinyML Voice-Recognition Application on Resource Frugal Edge Devices
Kwon, J., & Park, D. (2021) · Applied Sciences · doi:10.3390/app112211073 · Cited by 36
The synergy of complex event processing and tiny machine learning in industrial IoT
Ren, H., Anicic, D., & Runkler, T. A. (2021) · ACM International Conference on Distributed and Event-Based Systems (DEBS) · doi:10.1145/3465480.3466928 · Cited by 36
“Impressive results have been achieved recently, such as tinyML algorithm [32][25], hardware [10][9], and application [34][5].”
BackgroundDNN Is Not All You Need: Parallelizing Non-neural ML Algorithms on Ultra-low-power IoT Processors
Tabanelli, E., Tagliavini, G., & Benini, L. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3571133 · Cited by 48
“Furthermore, commercial devices such as 16-bit PIC and MSP430 4 MCUs, along with Xtensa L106 core embedded into ESP8266 SoCs 5 , follow this trend.”
MethodInfluentialDNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors
Tabanelli, E., Tagliavini, G., & Benini, L. (2021) · arXiv · doi:10.48550/arxiv.2107.09448 · Cited by 36
“Furthermore, commercial devices such as 16-bit PIC and MSP430 4 MCUs, along with Xtensa L106 core embedded into ESP8266 SoCs 5 , follow this trend.”
MethodInfluentialDeep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
Asutkar, S., & Tallur, S. G. (2023) · Scientific Reports · doi:10.1038/s41598-023-33887-5 · Cited by 40
Dynamic AI-IoT: Enabling Updatable AI Models in Ultralow-Power 5G IoT Devices
Alselek, M., Calero, J. M. A., & Wang, Q. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3340858 · Cited by 34
“In the context of these developments, Edge Impulse Studio, a cloud-based platform dedicated to embedded machine learning, has played a vital role in facilitating model training, evaluation, and subsequent deployment on IoT devices at the network’s edge [17].”
BackgroundMethodOsman, A., Abid, U., Gemma, L., Perotto, M., & Brunelli, D. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-3-030-95498-7_20 · Cited by 34
Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications
Campolo, C., Genovese, G., Iera, A., & Molinaro, A. (2021) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan10010013 · Cited by 33
“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…”
Automatic Distributed Deep Learning Using Resource-Constrained Edge Devices
Gutierrez-Torre, A., Bahadori, K., Baig, S.-U.-R., Iqbal, W., Vardanega, T., Berral, J. L., & Carrera, D. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3098973 · Cited by 32
Survey and Comparison of Milliwatts Micro controllers for Tiny Machine Learning at the Edge
Giordano, M., Piccinelli, L., & Magno, M. (2022) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas54282.2022.9870017 · Cited by 31
“In [10] and [3] several possible use of TinyML systems are analysed, and a exhaustive survey of edge machine learning frameworks is reported.”
BackgroundThe role of vehicular applications in the design of future 6G infrastructures
Gallego-Madrid, J., Sanchez‐Iborra, R., Ortiz, J., & Santa, J. (2023) · ICT Express · doi:10.1016/j.icte.2023.03.011 · Cited by 31
Self-citationtinyCare: A tinyML-based Low-Cost Continuous Blood Pressure Estimation on the Extreme Edge
Ahmed, K., & Hassan, M. (2022) · 2022 IEEE 10th International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi54592.2022.00047 · Cited by 29
“Healthcare is identified as one of the sectors that will have the greatest growth potential when adopting tinyML [18].”
BackgroundTraining-free neural architecture search: A review
Wu, M., & Tsai, C. (2023) · ICT Express · doi:10.1016/j.icte.2023.11.001 · Cited by 31
Kashyap, P., Shivgan, K., Patil, S., Buddala, R. R., Mahajan, S., Banerjee, S., & Tallur, S. G. (2024) · Scientific Reports · doi:10.1038/s41598-024-54418-w · Cited by 29
“Recently, [15] demonstrated a method which utilizes supervised convolutional neural networks (CNNs) to learn the features of GW signals acquired from healthy and damage structures for varying temperature conditions, combined with GMMs for damage index computation and localization.”
MethodA Holistic Review of the TinyML Stack for Predictive Maintenance
Njor, E., Hasanpour, M. A., Madsen, J., & Fafoutis, X. (2024) · IEEE Access · doi:10.1109/access.2024.3512860 · Cited by 38
“TinyML, however, sees applications in many other fields, including healthcare [16], environmental control [24], and the transportation sector [8].”
Intelligent and Efficient IoT Through the Cooperation of TinyML and Edge Computing
Sanchez-Iborra, R., Zoubir, A., Hamdouchi, A., Idri, A., & Skarmeta, A. (2023) · Informatica · doi:10.15388/22-infor505 · Cited by 28
Self-citationA TinyML approach to non-repudiable anomaly detection in extreme industrial environments
Antonini, M., Pincheira, M., Vecchio, M., & Antonelli, F. (2022) · 2022 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4.0&IoT) · doi:10.1109/metroind4.0iot54413.2022.9831517 · Cited by 28
Malviya, V., Mukherjee, I., & Tallur, S. G. (2022) · IEEE Sensors Letters · doi:10.1109/lsens.2022.3159972 · Cited by 28
Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities
Saradopoulos, I. V., Potamitis, I., Ntalampiras, S., Konstantaras, A. J., & Antonidakis, E. N. (2022) · Sensors · doi:10.3390/s22052006 · Cited by 27
Vergel, Á. J. S., Velez, J. C., Amaya–Mier, R., & Pardo, M. (2023) · International Journal of Disaster Risk Reduction · doi:10.1016/j.ijdrr.2023.104094 · Cited by 28
TinyML in Africa: Opportunities and Challenges
Ooko, S. O., Muyonga Ogore, M., Nsenga, J., & Zennaro, M. (2021) · 2021 IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps52748.2021.9682107 · Cited by 29
Adaptive Traffic Control With TinyML
Roshan, A. N., Gokulapriyan, B., Siddarth, C., & Kokil, P. (2021) · 2021 Sixth International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) · doi:10.1109/wispnet51692.2021.9419472 · Cited by 27
“RFR was the choice of the ML model due to its low compute and memory requirements [15,16].”
MethodBackcasting frugally innovative smart sustainable future cities
Ebolor, A. (2022) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2022.135300 · Cited by 25
Embedded Artificial Intelligence: A Comprehensive Literature Review
Huang, X., Wang, H., Qin, S., & Tang, S.-K. (2025) · Electronics · doi:10.3390/electronics14173468 · Cited by 33
Dere, M. D., Jo, J.-H., & Lee, B. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3323962 · Cited by 22
“…performance of deep neural networks (DNNs) in various application domains, the mismatch between the resources of embedded devices and the computational complexity of DNN decoders poses a significant challenge for the deployment of DNN decoders at the edge for real-time inference [23], [24].”
BackgroundA Survey of Model Compression Techniques for TinyML Applications
Lamaakal, I., Yahyati, C., Ouahbi, I., Makkaoui, K. E., & Maleh, Y. (2025) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc66714.2025.11135279 · Cited by 22
“…including but not limited to: speech recognition in smart assistants [10], environmental monitoring with wireless sensor networks [11], predictive maintenance in industrial machinery [12], gesture and activity recognition in wearables [13]–[16], and object detection in autonomous systems [17].”
Optimizing Random Forest-Based Inference on RISC-V MCUs at the Extreme Edge
Tabanelli, E., Tagliavini, G., & Benini, L. (2022) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2022.3199903 · Cited by 25
“The paradigm shift toward near-sensor processing on resource-constrained devices is referred to as tinyML [13], [14], [15].”
BackgroundEnergy efficient Firmware Over The Air Update for TinyML models in LoRaWAN agricultural networks
Chollet, N., Bouchemal, N., & Ramdane-Chérif, A. (2022) · International Telecommunication Networks and Applications Conference (ITNAC) · doi:10.1109/itnac55475.2022.9998338 · Cited by 22
Li, T., Luo, J., Liang, K., Yi, C., & Ma, L. (2023) · Sustainability · doi:10.3390/su151813779 · Cited by 23
Empirical study of the modulus as activation function in computer vision applications
Vallés-Ṕerez, I., Soria‐Olivas, E., Martínez-Sober, M., Serrano-López, A. J., Vila‐Francés, J., & Gómez‐Sanchís, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.105863 · Cited by 27
The Case for tinyML in Healthcare: CNNs for Real-Time On-Edge Blood Pressure Estimation
Sun, B., Bayes, S., Abotaleb, A. M., & Hassan, M. (2023) · ACM Symposium on Applied Computing · doi:10.1145/3555776.3577747 · Cited by 25
Towards Semantic Management of On-Device Applications in Industrial IoT
Ren, H., Anicic, D., & Runkler, T. A. (2022) · ACM Transactions on Internet Technology · doi:10.1145/3510820 · Cited by 20
“Impressive results have been made with TinyML (see work related to hardware [15] and [16], and applications [49] and [54]).”
BackgroundEfficient People Counting in Thermal Images: The Benchmark of Resource-Constrained Hardware
Piechocki, M., Kraft, M., Pajchrowski, T., Aszkowski, P., & Pieczyński, D. (2022) · IEEE Access · doi:10.1109/access.2022.3225233 · Cited by 23
“[13] recognize as energy efficiency, low cost and latency, system reliability, and data security.”
BackgroundGamazo-Real, J.-C., Fernández, R. T., & Armas, A. M. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107149 · Cited by 20
Standalone edge AI-based solution for Tomato diseases detection
Majeed, Y., Ojo, M. O., & Zahid, A. (2024) · Smart Agricultural Technology · doi:10.1016/j.atech.2024.100547 · Cited by 30
Ashkarkalaei, M., Ghiasi, R., Pakrashi, V., & Malekjafarian, A. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.112568 · Cited by 19
Ali, E. M., Abawajy, J., Lemma, F., & Baho, S. A. (2025) · Sensors · doi:10.3390/s25175286 · Cited by 19
“Sanchez-Iborra and Skarmeta [132] discuss the application of TinyML for human lives, and a survey by Abadade et al. [133] also presents the application of TinyML for different domains such as precision agriculture, disaster risk management, smart appliances, optimizing energy utilization, wearable…”
A Primer for tinyML Predictive Maintenance: Input and Model Optimisation
Njor, E., Madsen, J., & Fafoutis, X. (2022) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-08337-2_6 · Cited by 20
“The survey concludes with a case study, for which a decision tree model is deemed the best tinyML model choice [26].”
Influential
Metadata
- Authors
- Sanchez-Iborra, R., & Skarmeta, A. F.
- Venue
- IEEE Circuits and Systems Magazine
- Published
- 2020
- Volume
- 20
- Issue
- 3
- Pages
- 4-18
- ISSN
- 0163-6812 (ISSN-L)
- 1531-636X
- 1558-0830
- 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
- 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
