Intelligent and Efficient IoT Through the Cooperation of TinyML and Edge Computing
Volume 34, Issue 1 (2023), pp. 147–168
Pub. online: 10 January 2023
Type: Research Article
Open Access
Open Access
Received
1 September 2021
1 September 2021
Accepted
1 November 2022
1 November 2022
Published
10 January 2023
10 January 2023
Abstract
The coordinated integration of heterogeneous TinyML-enabled elements in highly distributed Internet of Things (IoT) environments paves the way for the development of truly intelligent and context-aware applications. In this work, we propose a hierarchical ensemble TinyML scheme that permits system-wide decisions by considering the individual decisions made by the IoT elements deployed in a certain scenario. A two-layered TinyML-based edge computing solution has been implemented and evaluated in a real smart-agriculture use case, permitting to save wireless transmissions, reduce energy consumption and response times, at the same time strengthening data privacy and security.
References
Abdel-Basset, M., Manogaran, G., Gamal, A., Chang, V. (2020). A novel intelligent medical decision support model based on soft computing and IoT. IEEE Internet of Things Journal, 7(5), 4160–4170. https://doi.org/10.1109/JIOT.2019.2931647. https://ieeexplore.ieee.org/document/8787865/.
Alaba, F.A., Othman, M., Hashem, I.A.T., Alotaibi, F. (2017). Internet of things security: a survey. Journal of Network and Computer Applications, 88, 10–28. https://doi.org/10.1016/j.jnca.2017.04.002. https://linkinghub.elsevier.com/retrieve/pii/S1084804517301455.
Alongi, F., Nicolò, G., Danilo, P., Terraneo, F., Fornaciari, W. (2020). Tiny neural networks for environmental predictions: an integrated approach with Miosix. In: Fifth IEEE Workshop on Smart Service Systems (SmartSys 2020), pp. 350–355. https://doi.org/10.1109/SMARTCOMP50058.2020.00076.
Ashouri, M., Davidsson, P., Spalazzese, R. (2018). Cloud, edge, or both? Towards decision support for designing IoT applications. In: 2018 Fifth International Conference on Internet of Things: Systems, Management and Security, pp. 155–162. https://doi.org/10.1109/IoTSMS.2018.8554827. https://ieeexplore.ieee.org/document/8554827/.
Atitallah, S.B., Driss, M., Boulila, W., Ghézala, H.B. (2020). Leveraging deep learning and IoT big data analytics to support the smart cities development: review and future directions. Computer Science Review, 38, 100303. https://doi.org/10.1016/j.cosrev.2020.100303. https://linkinghub.elsevier.com/retrieve/pii/S1574013720304032.
Bormann, C., Ersue, M., Keranen, A. (2014). Terminology for constrained-node networks. In: IETF RFC 7228. https://doi.org/10.17487/RFC7228. https://www.rfc-editor.org/info/rfc7228.
Breitbach, M., Schafer, D., Edinger, J., Becker, C. (2019). Context-aware data and task placement in edge computing environments. In: IEEE International Conference on Pervasive Computing and Communications (PerCom), pp. 1–10. https://doi.org/10.1109/PERCOM.2019.8767386. https://ieeexplore.ieee.org/document/8767386/.
Chao, L., Wen-hui, Z., Ran, L., Jun-yi, W., Ji-ming, L. (2020). Research on star/galaxy classification based on stacking ensemble learning. Chinese Astronomy and Astrophysics, 44(3), 345–355. https://doi.org/10.1016/j.chinastron.2020.08.005. https://linkinghub.elsevier.com/retrieve/pii/S0275106220300783.
Chatzimparmpas, A., Martins, R.M., Kucher, K., Kerren, A. (2021). StackGenVis: alignment of data, algorithms, and models for stacking ensemble learning using performance metrics. IEEE Transactions on Visualization and Computer Graphics, 27(2), 1547–1557. https://doi.org/10.1109/TVCG.2020.3030352. https://ieeexplore.ieee.org/document/9222343/.
Cheng, C., Xu, P.-F., Cheng, H., Ding, Y., Zheng, J., Ge, T., Sun, D., Xu, J. (2020). Ensemble learning approach based on stacking for unmanned surface vehicle’s dynamics. Ocean Engineering, 207, 107388. https://doi.org/10.1016/j.oceaneng.2020.107388. https://linkinghub.elsevier.com/retrieve/pii/S0029801820304170.
Cirillo, F., Wu, F.-J., Solmaz, G., Kovacs, E. (2019). Embracing the future Internet of things. Sensors, 19(2), 351. https://doi.org/10.3390/s19020351. https://www.mdpi.com/1424-8220/19/2/351.
Cui, L., Xu, C., Yang, S., Huang, J.Z., Li, J., Wang, X., Ming, Z., Lu, N. (2019). Joint optimization of energy consumption and latency in mobile edge computing for Internet of things. IEEE Internet of Things Journal, 6(3), 4791–4803. https://doi.org/10.1109/JIOT.2018.2869226. https://ieeexplore.ieee.org/document/8457190/.
de Prado, M., Donze, R., Capotondi, A., Rusci, M., Monnerat, S., Benini, L., Pazos, N. (2020). Robust Navigation with TinyML for Autonomous Mini-Vehicles. arXiv preprint: arXiv:2007.00302.
Elwerghemmi, R., Heni, M., Ksantini, R., Bouallegue, R. (2019). Online QoE prediction model based on stacked multiclass incremental support vector machine. In: 8th International Conference on Modeling Simulation and Applied Optimization (ICMSAO), pp. 1–5. https://doi.org/10.1109/ICMSAO.2019.8880302. https://ieeexplore.ieee.org/document/8880302/.
Emre Isik, Y., Gormez, Y., Kaynar, O., Aydin, Z. (2018). NSEM: novel stacked ensemble method for sentiment analysis. In: International Conference on Artificial Intelligence and Data Processing (IDAP), pp. 1–4. https://doi.org/10.1109/IDAP.2018.8620913. https://ieeexplore.ieee.org/document/8620913/.
Hadj Sassi, M.S., Jedidi, F.G., Fourati, L.C. (2019). A new architecture for cognitive Internet of things and big data. Procedia Computer Science, 159, 534–543. https://doi.org/10.1016/j.procs.2019.09.208. https://linkinghub.elsevier.com/retrieve/pii/S1877050919313924.
Kowsari, K., Brown, D.E., Heidarysafa, M., Jafari Meimandi, K., Gerber, M.S., Barnes, L.E. (2017). HDLTex: hierarchical deep learning for text classification. In: 16th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 364–371. https://doi.org/10.1109/ICMLA.2017.0-134. http://ieeexplore.ieee.org/document/8260658/.
Ksia̧żek, W., Hammad, M., Pławiak, P., Acharya, U.R., Tadeusiewicz, R. (2020). Development of novel ensemble model using stacking learning and evolutionary computation techniques for automated hepatocellular carcinoma detection. Biocybernetics and Biomedical Engineering, 40(4), 1512–1524. https://doi.org/10.1016/j.bbe.2020.08.007. https://linkinghub.elsevier.com/retrieve/pii/S0208521620300991.
Liu, Q., Cheng, L., Ozcelebi, T., Murphy, J., Lukkien, J. (2019). Deep reinforcement learning for IoT network dynamic clustering in edge computing. In: 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), pp. 600–603. https://doi.org/10.1109/CCGRID.2019.00077. https://ieeexplore.ieee.org/document/8752691/.
Lopez Pena, M.A., Munoz Fernandez, I. (2019). SAT-IoT: an architectural model for a high-performance fog/edge/cloud IoT platform. In: 2019 IEEE 5th World Forum on Internet of Things (WF-IoT), pp. 633–638. https://doi.org/10.1109/WF-IoT.2019.8767282. https://ieeexplore.ieee.org/document/8767282/.
Marjanovic, M., Antonic, A., Zarko, I.P. (2018). Edge computing architecture for mobile crowdsensing. IEEE Access, 6, 10662–10674. https://doi.org/10.1109/ACCESS.2018.2799707. http://ieeexplore.ieee.org/document/8272334/.
Mocnej, J., Miškuf, M., Papcun, P., Zolotová, I. (2018). Impact of edge computing paradigm on energy consumption in IoT. IFAC-PapersOnLine, 51(6), 162–167. https://doi.org/10.1016/j.ifacol.2018.07.147. https://www.sciencedirect.com/science/article/pii/S2405896318308917.
Mounica, R.O., Soumya, V., Krovvidi, S., Chandrika, K.S., Gayathri, R. (2019). A multi layer ensemble learning framework for learning disability detection in school-aged children. In: 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pp. 1–6. https://doi.org/10.1109/ICCCNT45670.2019.8944774. https://ieeexplore.ieee.org/document/8944774/.
Mrozek, D., Koczur, A., Małysiak-Mrozek, B. (2020). Fall detection in older adults with mobile IoT devices and machine learning in the cloud and on the edge. Information Sciences, 537, 132–147. https://doi.org/10.1016/j.ins.2020.05.070. https://linkinghub.elsevier.com/retrieve/pii/S0020025520304886.
Pavlyshenko, B. (2018). Using stacking approaches for machine learning models. In: IEEE Second International Conference on Data Stream Mining & Processing (DSMP), pp. 255–258. https://doi.org/10.1109/DSMP.2018.8478522. https://ieeexplore.ieee.org/document/8478522/.
Porambage, P., Okwuibe, J., Liyanage, M., Ylianttila, M., Taleb, T. (2018). Survey on multi-access edge computing for Internet of things realization. IEEE Communications Surveys & Tutorials, 20(4), 2961–2991. https://doi.org/10.1109/COMST.2018.2849509. https://ieeexplore.ieee.org/document/8391395/.
Raj, M., Gupta, S., Chamola, V., Elhence, A., Garg, T., Atiquzzaman, M., Niyato, D. (2021). A survey on the role of Internet of things for adopting and promoting Agriculture 4.0. Journal of Network and Computer Applications, 187, 103107. https://doi.org/10.1016/j.jnca.2021.103107. https://linkinghub.elsevier.com/retrieve/pii/S1084804521001284.
Rokach, L. (2010). Ensemble-based classifiers. Artificial Intelligence Review, 33(1–2), 1–39. https://doi.org/10.1007/s10462-009-9124-7. http://link.springer.com/10.1007/s10462-009-9124-7.
Sanchez-Gomez, J., Gallego-Madrid, J., Sanchez-Iborra, R., Skarmeta, A.F. (2019). Performance study of LoRaWAN for smart-city applications. In: IEEE 2nd 5G World Forum (5GWF), pp. 58–62. https://doi.org/10.1109/5GWF.2019.8911676. https://ieeexplore.ieee.org/document/8911676/.
Sanchez-Gomez, J., Gallego-Madrid, J., Sanchez-Iborra, R., Santa, J., Skarmeta Gómez, A.F. (2020). Impact of SCHC compression and fragmentation in LPWAN: a case study with LoRaWAN. Sensors, 20(1), 280. https://doi.org/10.3390/s20010280. https://www.mdpi.com/1424-8220/20/1/280.
Sanchez-Iborra, R., Cano, M.-D. (2016). State of the art in LP-WAN solutions for industrial IoT services. Sensors, 16(5), 708. https://doi.org/10.3390/s16050708. http://www.mdpi.com/1424-8220/16/5/708/htm.
Sanchez-Iborra, R., Skarmeta, A.F. (2020). TinyML-enabled frugal smart objects: challenges and opportunities. IEEE Circuits and Systems Magazine, 20(3), 4–18. https://doi.org/10.1109/MCAS.2020.3005467. https://ieeexplore.ieee.org/document/9166461/.
Sanchez-Iborra, R., Sanchez-Gomez, J., Skarmeta, A. (2018). Evolving IoT networks by the confluence of MEC and LP-WAN paradigms. Future Generation Computer Systems, 88, 199–208. https://doi.org/10.1016/j.future.2018.05.057. http://linkinghub.elsevier.com/retrieve/pii/S0167739X17324159.
Santa, J., Fernández, P.J., Sanchez-Iborra, R., Ortiz, J., Skarmeta, A.F. (2018). Offloading positioning onto network edge. Wireless Communications and Mobile Computing, 2018, 1–13. https://doi.org/10.1155/2018/7868796. https://www.hindawi.com/journals/wcmc/2018/7868796/.
Santa, J., Skarmeta, A.F., Ortiz, J., Fernandez, P.J., Luis, M., Gomes, C., Oliveira, J., Gomes, D., Sanchez-Iborra, R., Sargento, S. (2020). MIGRATE: mobile device virtualisation through state transfer. IEEE Access, 8, 25848–25862. https://doi.org/10.1109/ACCESS.2020.2971090. https://ieeexplore.ieee.org/document/8978626/.
Semtech (2019). SX1272 LoRa Modem Datasheet v4. Technical report. https://www.semtech.com/products/wireless-rf/lora-transceivers/sx1272.
Silva, C., Ribeiro, B. (2006). Two-level hierarchical hybrid SVM-RVM classification model. In: 5th International Conference on Machine Learning and Applications (ICMLA’06), pp. 89–94. 0-7695-2735-3. https://doi.org/10.1109/ICMLA.2006.52. http://ieeexplore.ieee.org/document/4041475/.
Song, Y., Yau, S.S., Yu, R., Zhang, X., Xue, G. (2017). An approach to QoS-based task distribution in edge computing networks for IoT applications. In: IEEE International Conference on Edge Computing (EDGE), pp. 32–39. https://doi.org/10.1109/IEEE.EDGE.2017.50. http://ieeexplore.ieee.org/document/8029254/.
van Klompenburg, T., Kassahun, A., Catal, C. (2020). Crop yield prediction using machine learning: a systematic literature review. Computers and Electronics in Agriculture, 177, 105709. https://doi.org/10.1016/j.compag.2020.105709. https://linkinghub.elsevier.com/retrieve/pii/S0168169920302301.
Veeramanikandan, Sankaranarayanan, S., Rodrigues, J.J.P.C., Sugumaran, V., Kozlov, S. (2020). Data flow and distributed deep neural network based low latency IoT-edge computation model for big data environment. Engineering Applications of Artificial Intelligence, 94, 103785. https://doi.org/10.1016/j.engappai.2020.103785. https://linkinghub.elsevier.com/retrieve/pii/S0952197620301780.
Vuppalapati, C., Ilapakurti, A., Kedari, S., Vuppalapati, J., Kedari, S., Vuppalapati, R. (2020). Democratization of AI, Albeit constrained IoT devices & tiny ML, for creating a sustainable food future. In: 3rd International Conference on Information and Computer Technologies (ICICT), pp. 525–530. https://doi.org/10.1109/ICICT50521.2020.00089. https://ieeexplore.ieee.org/document/9092247/.
Wang, X., Wang, X., Li, Y. (2021). NDN-based IoT with edge computing. Future Generation Computer Systems, 115, 397–405. https://doi.org/10.1016/j.future.2020.09.018. https://linkinghub.elsevier.com/retrieve/pii/S0167739X20303903.
Wang, Y., Wang, D., Geng, N., Wang, Y., Yin, Y., Jin, Y. (2019). Stacking-based ensemble learning of decision trees for interpretable prostate cancer detection. Applied Soft Computing, 77, 188–204. https://doi.org/10.1016/j.asoc.2019.01.015. https://linkinghub.elsevier.com/retrieve/pii/S1568494619300195.
Wolpert, D.H. (1992). Stacked generalization. Neural Networks, 5(2), 241–259. https://doi.org/10.1016/S0893-6080(05)80023-1. https://linkinghub.elsevier.com/retrieve/pii/S0893608005800231.
Wong, A., Famouri, M., Shafiee, M.J. (2020). AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers. arXiv preprint: arXiv:2009.14385.
Xu, X., Liu, Q., Luo, Y., Peng, K., Zhang, X., Meng, S., Qi, L. (2019). A computation offloading method over big data for IoT-enabled cloud-edge computing. Future Generation Computer Systems, 95, 522–533. https://doi.org/10.1016/j.future.2018.12.055. https://linkinghub.elsevier.com/retrieve/pii/S0167739X18319770.
Biographies
Sanchez-Iborra Ramon
R. Sanchez-Iborra is an assistant professor at the University Centre of Defense at the General Air Force Academy (Spain). He graduated from the Technical University of Cartagena (Spain), received the BSc degree in telecommunication engineering in 2007 and the MSc and PhD degrees in information and communication technologies in 2013 and 2015, respectively. He has published more than 50 papers in international journals and conferences. His main research interests are IoT/M2M architectures, management of wireless networks, and green networking techniques.
Zoubir Abdeljalil
A. Zoubir graduated in 2018 from the Royal Air School-Marrakesh with a state engineering diploma in aeronautical systems. In 2021, he will receive his master’s degree in data science. He is currently pursuing a PhD in data sciences at Mohammed VI Polytechnic University (Morocco). His research interests include embedded machine learning, graph neural networks and their applications in medicine, and distributed intelligent systems.
Hamdouchi Abderahmane
A. Hamdouchi is a PhD student in data science at Mohammed VI Polytechnic University (Morocco). He earned a BSc in mechanical engineering from the Royal Military Academy (Morocco) in 2013 and a Diploma of Analyst in computer science from the Signal Training Centre in 2017. He received his master’s degree in data science in 2021. His primary research interests are real-time decision support systems and TinyML systems.
Idri Ali
A. Idri is a full professor at the Computer Science and Systems Analysis School (ENSIAS, Mohammed V University in Rabat, Morocco). He received his master and doctorate of 3rd cycle in computer science from the Mohammed V University in 1994 and 1997, respectively. He received his PhD in cognitive and computer sciences from the University of Quebec at Montreal in 2003. He was the chair of the Web and Mobile Engineering Department for the period 2014–2020 and currently he is the head of the Software Project Management Research Team since 2010. He is very active in the fields of artificial intelligence, machine learning, medical informatics, software engineering, and has published more than 220 papers in well recognized journals and conferences.
Skarmeta Antonio
A. Skarmeta received the BS degree (Hons.) from the University of Murcia, Spain, the MS degree from the University of Granada, and the PhD degree from the University of Murcia, all in computer science. He has been a full professor with the University of Murcia, since 2009. He has taken part in many EU FP projects and even coordinated some of them. He has published more than 200 international articles. His main interests include the integration of security services, identity, the IoT, 5G, and smart cities.
