{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:32:05Z","timestamp":1773693125802,"version":"3.50.1"},"reference-count":66,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T00:00:00Z","timestamp":1612310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["TIN2017-85409-P"],"award-info":[{"award-number":["TIN2017-85409-P"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep learning techniques are being increasingly used in the scientific community as a consequence of the high computational capacity of current systems and the increase in the amount of data available as a result of the digitalisation of society in general and the industrial world in particular. In addition, the immersion of the field of edge computing, which focuses on integrating artificial intelligence as close as possible to the client, makes it possible to implement systems that act in real time without the need to transfer all of the data to centralised servers. The combination of these two concepts can lead to systems with the capacity to make correct decisions and act based on them immediately and in situ. Despite this, the low capacity of embedded systems greatly hinders this integration, so the possibility of being able to integrate them into a wide range of micro-controllers can be a great advantage. This paper contributes with the generation of an environment based on Mbed OS and TensorFlow Lite to be embedded in any general purpose embedded system, allowing the introduction of deep learning architectures. The experiments herein prove that the proposed system is competitive if compared to other commercial systems.<\/jats:p>","DOI":"10.3390\/s21041031","type":"journal-article","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T20:31:51Z","timestamp":1612384311000},"page":"1031","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["A Generalization Performance Study Using Deep Learning Networks in Embedded Systems"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0334-5509","authenticated-orcid":false,"given":"Joseba","family":"Gorospe","sequence":"first","affiliation":[{"name":"TECNALIA, Basque Research and Technology Alliance (BRTA), Astondo Bidea Building 700, 48160 Derio, Spain"},{"name":"Electronics and Computer Science Department, Mondragon Unibertsitatea, Loramendi 4, 20500 Arrasate-Mondragon, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6341-5161","authenticated-orcid":false,"given":"Rub\u00e9n","family":"Mulero","sequence":"additional","affiliation":[{"name":"TECNALIA, Basque Research and Technology Alliance (BRTA), Astondo Bidea Building 700, 48160 Derio, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7371-2971","authenticated-orcid":false,"given":"Olatz","family":"Arbelaitz","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, University of the Basque Country UPV\/EHU, Manuel Lardizabal 1, 20018 Donostia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7026-7371","authenticated-orcid":false,"given":"Javier","family":"Muguerza","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, University of the Basque Country UPV\/EHU, Manuel Lardizabal 1, 20018 Donostia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3775-2906","authenticated-orcid":false,"given":"Miguel \u00c1ngel","family":"Ant\u00f3n","sequence":"additional","affiliation":[{"name":"TECNALIA, Basque Research and Technology Alliance (BRTA), Astondo Bidea Building 700, 48160 Derio, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,3]]},"reference":[{"key":"ref_1","unstructured":"Jackson, P. (1998). Introduction to Expert Systems, Addison-Wesley Longman Publishing Co., Inc."},{"key":"ref_2","first-page":"2","article-title":"Introduction to machine learning","volume":"7","author":"Mitchell","year":"1997","journal-title":"Mach. Learn."},{"key":"ref_3","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Jadeja, Y., and Modi, K. (2012, January 21\u201322). Cloud computing\u2014Concepts, architecture and challenges. Proceedings of the International Conference on Computing, Electronics and Electrical Technologies (ICCEET), Kumaracoil, India.","DOI":"10.1109\/ICCEET.2012.6203873"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Rao, B.B.P., Saluia, P., Sharma, N., Mittal, A., and Sharma, S.V. (2012, January 18\u201321). Cloud computing for Internet of Things sensing based applications. Proceedings of the Sixth International Conference on Sensing Technology (ICST), Kolkata, India.","DOI":"10.1109\/ICSensT.2012.6461705"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Davis, A., Parikh, J., and Weihl, W.E. (2004, January 17\u201320). Edgecomputing: Extending enterprise applications to the edge of the internet. Proceedings of the 13th international World Wide Web Conference on Alternate Track Papers & Posters, New York, NY, USA.","DOI":"10.1145\/1010432.1010462"},{"key":"ref_7","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e00938","DOI":"10.1016\/j.heliyon.2018.e00938","article-title":"State-of-the-art in artificial neural network applications: A survey","volume":"4","author":"Abiodun","year":"2018","journal-title":"Heliyon"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/S0169-7439(97)00061-0","article-title":"Introduction to multi-layer feed-forward neural networks","volume":"39","author":"Svozil","year":"1997","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2923","DOI":"10.1109\/COMST.2018.2844341","article-title":"Deep Learning for IoT Big Data and Streaming Analytics: A Survey","volume":"20","author":"Mohammadi","year":"2018","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_11","unstructured":"Glorot, X., Bordes, A., and Bengio, Y. (2010, January 11\u201313). Deep Sparse Rectifier Neural Networks. Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, Ft. Lauderdale, FL, USA."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., and Doya, K. (2017). Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning. arXiv.","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref_13","unstructured":"Clevert, D.A., Unterthiner, T., and Hochreiter, S. (2015). Fast and accurate deep network learning by exponential linear units (elus). arXiv."},{"key":"ref_14","unstructured":"Sutskever, I., Martens, J., Dahl, G., and Hinton, G. (2013, January 16\u201321). On the importance of initialization and momentum in deep learning. Proceedings of the 30th International Conference on Machine Learning (ICML), Atlanta, GA, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A Deep Learning Approach to Antibiotic Discovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1016\/j.future.2017.08.043","article-title":"Distributed attack detection scheme using deep learning approach for Internet of Things","volume":"82","author":"Diro","year":"2018","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","article-title":"Recent Trends in Deep Learning Based Natural Language Processing [Review Article]","volume":"13","author":"Young","year":"2018","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"7068349","DOI":"10.1155\/2018\/7068349","article-title":"Deep Learning for Computer Vision: A Brief Review","volume":"2018","author":"Voulodimos","year":"2018","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1007\/s11063-019-10115-8","article-title":"Traffic signs detection for real-world application of an advanced driving assisting system using deep learning","volume":"51","author":"Ayachi","year":"2020","journal-title":"Neural Process. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"510","DOI":"10.3389\/fpls.2020.00510","article-title":"Recognition and Localization Methods for Vision-Based Fruit Picking Robots: A Review","volume":"11","author":"Tang","year":"2020","journal-title":"Front. Plant Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1007\/s10845-020-01549-2","article-title":"Quality analysis in metal additive manufacturing with deep learning","volume":"31","author":"Li","year":"2020","journal-title":"J. Intell. Manuf."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1236021","DOI":"10.1155\/2020\/1236021","article-title":"Vision-Based Three-Dimensional Reconstruction and Monitoring of Large-Scale Steel Tubular Structures","volume":"2020","author":"Tang","year":"2020","journal-title":"Adv. Civ. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1109\/72.80236","article-title":"A simple procedure for pruning back-propagation trained neural networks","volume":"1","author":"Karnin","year":"1990","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_24","unstructured":"Blalock, D., Ortiz, J.J.G., Frankle, J., and Guttag, J. (2020). What is the State of Neural Network Pruning?. arXiv."},{"key":"ref_25","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H.P. (2017). Pruning Filters for Efficient ConvNets. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., and Sun, J. (2017). Channel Pruning for Accelerating Very Deep Neural Networks. arXiv.","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref_27","unstructured":"Lee, N., Ajanthan, T., and Torr, P.H.S. (2019). SNIP: Single-shot Network Pruning based on Connection Sensitivity. arXiv."},{"key":"ref_28","unstructured":"Liu, Z., Sun, M., Zhou, T., Huang, G., and Darrell, T. (2019). Rethinking the Value of Network Pruning. arXiv."},{"key":"ref_29","unstructured":"Han, S., Pool, J., Tran, J., and Dally, W.J. (2015). Learning both Weights and Connections for Efficient Neural Networks. arXiv."},{"key":"ref_30","unstructured":"Gale, T., Elsen, E., and Hooker, S. (2019). The State of Sparsity in Deep Neural Networks. arXiv."},{"key":"ref_31","unstructured":"Frankle, J., Dziugaite, G.K., Roy, D.M., and Carbin, M. (2020). Stabilizing the Lottery Ticket Hypothesis. arXiv."},{"key":"ref_32","unstructured":"Gong, Y., Liu, L., Yang, M., and Bourdev, L. (2014). Compressing Deep Convolutional Networks using Vector Quantization. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","article-title":"Product Quantization for Nearest Neighbor Search","volume":"33","author":"Douze","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"11259","DOI":"10.3390\/s101211259","article-title":"Approximate Nearest Neighbor Search by Residual Vector Quantization","volume":"10","author":"Chen","year":"2010","journal-title":"Sensors"},{"key":"ref_35","first-page":"6869","article-title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","volume":"18","author":"Hubara","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1109\/TPAMI.2018.2886192","article-title":"Deep Neural Network Compression by In-Parallel Pruning-Quantization","volume":"42","author":"Tung","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Sindhwani, V., Arisoy, E., and Ramabhadran, B. (2013, January 26\u201331). Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada.","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref_38","unstructured":"Denton, E., Zaremba, W., Bruna, J., LeCun, Y., and Fergus, R. (2014). Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation. arXiv."},{"key":"ref_39","unstructured":"Cohen, T.S., and Welling, M. (2016). Group Equivariant Convolutional Networks. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., and Chen, L. (2018). Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. arXiv.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (2019). Searching for MobileNetV3. arXiv.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_42","unstructured":"Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size. arXiv."},{"key":"ref_43","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Luo, P., Zhu, Z., Liu, Z., Wang, X., and Tang, X. (2016, January 12\u201317). Face Model Compression by Distilling Knowledge from Neurons. Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.","DOI":"10.1609\/aaai.v30i1.10449"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1109\/JPROC.2019.2921977","article-title":"Deep Learning With Edge Computing: A Review","volume":"107","author":"Chen","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1109\/TSC.2017.2662008","article-title":"A New Deep Learning-Based Food Recognition System for Dietary Assessment on An Edge Computing Service Infrastructure","volume":"11","author":"Liu","year":"2018","journal-title":"IEEE Trans. Serv. Comput."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Amato, G., Carrara, F., Falchi, F., Gennaro, C., Meghini, C., and Vairo, C. (2016). Deep Learning for Decentralized Parking Lot Occupancy Detection. Expert Syst. Appl., 72.","DOI":"10.1016\/j.eswa.2016.10.055"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Liang, V.C., Ma, R.T.B., Ng, W.S., Wang, L., Winslett, M., Wu, H., Ying, S., and Zhang, Z. (2016, January 16\u201320). Mercury: Metro density prediction with recurrent neural network on streaming CDR data. Proceedings of the IEEE 32nd International Conference on Data Engineering (ICDE), Helsinki, Finland.","DOI":"10.1109\/ICDE.2016.7498348"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"5423","DOI":"10.1109\/JIOT.2019.2902141","article-title":"Deep Learning-Based Multiple Object Visual Tracking on Embedded System for IoT and Mobile Edge Computing Applications","volume":"6","author":"Brea","year":"2019","journal-title":"IEEE Internet Things J."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"71","DOI":"10.18201\/ijisae.2020261587","article-title":"Object Recognition with Hybrid Deep Learning Methods and Testing on Embedded Systems","volume":"8","author":"Taspinar","year":"2020","journal-title":"Int. J. Intell. Syst. Appl. Eng."},{"key":"ref_51","unstructured":"Soo, S. (2014). Object Detection Using Haar-Cascade Classifier, Institute of Computer Science, University of Tartu."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Zhong, C., Gursoy, M.C., and Velipasalar, S. (2018, January 21\u201323). A deep reinforcement learning-based framework for content caching. Proceedings of the 52nd Annual Conference on Information Sciences and Systems (CISS), Princeton, NJ, USA.","DOI":"10.1109\/CISS.2018.8362276"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Manogaran, G., Shakeel, P.M., Fouad, H., Nam, Y., Baskar, S., Chilamkurti, N.K., and Sundarasekar, R. (2019). Wearable IoT Smart-Log Patch: An Edge Computing-Based Bayesian Deep Learning Network System for Multi Access Physical Monitoring System. Sensors, 19.","DOI":"10.3390\/s19133030"},{"key":"ref_54","unstructured":"Banbury, C., Zhou, C., Fedorov, I., Navarro, R.M., Thakkar, U., Gope, D., Reddi, V.J., Mattina, M., and Whatmough, P.N. (2020). MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers. arXiv."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Lin, J., Chen, W.M., Lin, Y., Cohn, J., Gan, C., and Han, S. (2020). Mcunet: Tiny deep learning on iot devices. arXiv.","DOI":"10.1109\/IPCCC50635.2020.9391558"},{"key":"ref_56","unstructured":"Chen, T., Moreau, T., Jiang, Z., Zheng, L., Yan, E., Shen, H., Cowan, M., Wang, L., Hu, Y., and Ceze, L. (2018, January 8\u201310). {TVM}: An automated end-to-end optimizing compiler for deep learning. Proceedings of the 13th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 18), Carlsbad, CA, USA."},{"key":"ref_57","unstructured":"David, R., Duke, J., Jain, A., Reddi, V.J., Jeffries, N., Li, J., Kreeger, N., Nappier, I., Natraj, M., and Regev, S. (2020). TensorFlow lite micro: Embedded machine learning on tinyml systems. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., and Kalenichenko, D. (2018, January 18\u201322). Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref_59","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 7\u20139). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201322). Squeeze-and-Excitation Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_61","first-page":"1","article-title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","volume":"31","author":"Szegedy","year":"2017","journal-title":"AAAI Conf. Artif. Intell."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., and Le, Q.V. (2019, January 15\u201320). MnasNet: Platform-Aware Neural Architecture Search for Mobile. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, LA, USA.","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref_63","unstructured":"Chowdhery, A., Warden, P., Shlens, J., Howard, A., and Rhodes, R. (2019). Visual Wake Words Dataset. arXiv."},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Chandra, T.B., Verma, P., and Dwivedi, A. (2016, January 4\u20135). Operating systems for internet of things: A comparative study. Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies, Udaipur, India.","DOI":"10.1145\/2905055.2905105"},{"key":"ref_65","unstructured":"Borgohain, T., Kumar, U., and Sanyal, S. (2015). Survey of operating systems for the iot environment. arXiv."},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Sakr, F., Bellotti, F., Berta, R., and De Gloria, A. (2020). Machine Learning on Mainstream Microcontrollers. Sensors, 20.","DOI":"10.3390\/s20092638"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/4\/1031\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:19:26Z","timestamp":1760159966000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/4\/1031"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,3]]},"references-count":66,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["s21041031"],"URL":"https:\/\/doi.org\/10.3390\/s21041031","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,3]]}}}