{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,20]],"date-time":"2026-11-20T17:48:51Z","timestamp":1795196931703,"version":"4.10.3"},"reference-count":287,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:p>Edge Artificial Intelligence (AI) allows machine learning models to run directly on resource-constrained IoT and edge devices instead of relying only on cloud resources. This shift reduces latency and improves privacy but introduces strict constraints on memory, energy, and connectivity across heterogeneous sensor nodes. Deploying AI on constrained devices also requires addressing fragmented toolchains and inconsistent evaluation practices. This survey provides a structured review of deployment methods for edge AI, including model compilation, intermediate representations, hardware-aware optimization, scheduling strategies, and connectivity-aware execution. Post-deployment aspects are also examined, including lifecycle management, secure over-the-air updates, and benchmarking frameworks that combine latency, accuracy, and energy. Use cases in healthcare, smart cities, autonomous systems, manufacturing, and agriculture illustrate practical applications. Across these areas, common challenges in portability, reproducibility, adaptivity, and security are identified, along with emerging directions such as dynamic orchestration across heterogeneous devices and modular update mechanisms. By combining perspectives from compiler design, system optimization, and lifecycle management, this survey highlights how deployment pipelines are evolving into key enablers for reliable and scalable intelligence at the network edge.<\/jats:p>","DOI":"10.1145\/3827611","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T21:23:19Z","timestamp":1782422599000},"page":"1-53","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Edge AI on Constrained Devices: A Survey of Deployment, Optimization, and Lifecycle Management"],"prefix":"10.1145","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7447-2938","authenticated-orcid":false,"given":"Miriana","family":"Passarotto","sequence":"first","affiliation":[{"name":"RISE Research Institutes of Sweden AB","place":["Stockholm, Sweden"]},{"name":"Uppsala University","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7866-143X","authenticated-orcid":false,"given":"Fehmi","family":"Ben Abdesslem","sequence":"additional","affiliation":[{"name":"RISE Research Institutes of Sweden AB","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7257-4386","authenticated-orcid":false,"given":"Joakim","family":"Eriksson","sequence":"additional","affiliation":[{"name":"RISE Research Institutes of Sweden AB","place":["Stockholm, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2586-8573","authenticated-orcid":false,"given":"Thiemo","family":"Voigt","sequence":"additional","affiliation":[{"name":"Uppsala University","place":["Uppsala, Sweden"]},{"name":"RISE Research Institutes of Sweden AB","place":["Uppsala, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"2016. Raspberry Pi 3 Model B. Retrieved from https:\/\/www.raspberrypi.com\/products\/raspberry-pi-3-model-b\/"},{"key":"e_1_3_1_3_2","unstructured":"2017. Open Neural Network Exchange (ONNX). Retrieved from https:\/\/onnx.ai\/"},{"key":"e_1_3_1_4_2","unstructured":"2017. TensorFlow Lite. Retrieved from https:\/\/ai.google.dev\/edge\/litert"},{"key":"e_1_3_1_5_2","unstructured":"2018. ARM\u2019s Project Trillium Offers Scalable New Machine Learning Processors. Retrieved from https:\/\/newsroom.arm.com\/news\/arms-project-trillium-offers-the-industrys-most-scalable-versatile-ml-compute-platform"},{"key":"e_1_3_1_6_2","unstructured":"2019. Jetson Nano Developer Kit. Retrieved from https:\/\/developer.nvidia.com\/embedded\/jetson-nano"},{"key":"e_1_3_1_7_2","unstructured":"2025. AWS IoT Greengrass Documentation. Retrieved September 8 2025 from https:\/\/docs.aws.amazon.com\/greengrass\/v2\/developerguide\/what-is-gg.html"},{"key":"e_1_3_1_8_2","unstructured":"2025. Azure IoT Edge Documentation. Retrieved September 8 2025 from https:\/\/learn.microsoft.com\/en-us\/azure\/iot-edge\/about-iot-edge"},{"key":"e_1_3_1_9_2","unstructured":"2025. Balena IoT Fleet Management Platform. Retrieved September 2025 from https:\/\/www.balena.io\/"},{"key":"e_1_3_1_10_2","unstructured":"2025. Mender - OTA Software Updates for Linux Devices. Retrieved September 2025 from https:\/\/mender.io\/"},{"key":"e_1_3_1_11_2","unstructured":"2025. ONNX Runtime \u2014 Execution Providers. Retrieved September 8 2025 from https:\/\/onnxruntime.ai\/docs\/execution-providers\/"},{"key":"e_1_3_1_12_2","unstructured":"2025. Particle Cloud IoT platform. Retrieved September 2025 from https:\/\/www.particle.io\/"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps56602.2022.10008512"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2025.3542955"},{"key":"e_1_3_1_15_2","volume-title":"Proceedings of the IEEE\/ACM 16th International Conference on Utility and Cloud Computing","author":"Al-Ameen Shamil","year":"2024","unstructured":"Shamil Al-Ameen et\u00a0al. 2024. Tiny-Impute: A framework for on-device data quality validation, hybrid anomaly detection, and data imputation at the edge. In Proceedings of the IEEE\/ACM 16th International Conference on Utility and Cloud Computing. Association for Computing Machinery, Article 23. DOI:10.1145\/3603166.3632164"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2024.05.021"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23042344"},{"key":"e_1_3_1_18_2","unstructured":"Apache TVM Community. 2021. Apache TVM Unity: a vision for the ML software & hardware ecosystem in 2022. Retrieved from https:\/\/tvm.apache.org\/2021\/12\/15\/tvm-unity"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472292"},{"key":"e_1_3_1_20_2","unstructured":"ARM. 2024. ARM Trusted Firmware: Trusted Execution and Secure Boot. Retrieved from https:\/\/www.trustedfirmware.org\/"},{"key":"e_1_3_1_21_2","volume-title":"CMSIS-DSP: Overview","year":"2025","unstructured":"Arm. 2025. CMSIS-DSP: Overview. Retrieved August 21, 2025 from https:\/\/arm-software.github.io\/CMSIS-DSP\/main\/"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.01.034"},{"key":"e_1_3_1_23_2","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/WCADM.1995.514656","volume-title":"Proceedings Second Working Conference on Asynchronous Design Methodologies","author":"Arvind D. K.","year":"1995","unstructured":"D. K. Arvind, R. D. Mullins, and V. E. F. Rebello. 1995. Micronets: A model for decentralising control in asynchronous processor architectures. In Proceedings Second Working Conference on Asynchronous Design Methodologies. 190\u2013199. DOI:10.1109\/WCADM.1995.514656"},{"key":"e_1_3_1_24_2","first-page":"207","volume-title":"Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems (SenSys\u201922)","author":"Bakar Abu","year":"2023","unstructured":"Abu Bakar et\u00a0al. 2023. Protean: An energy-efficient and heterogeneous platform for adaptive and hardware-accelerated battery-free computing. In Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems (SenSys\u201922). Association for Computing Machinery, 207\u2013221. DOI:10.1145\/3560905.3568561"},{"key":"e_1_3_1_25_2","unstructured":"Colby Banbury et\u00a0al. 2021. MLPerf tiny benchmark. arXiv preprint arXiv:2106.07597 (2021). Retrieved from https:\/\/arxiv.org\/abs\/2106.07597"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Colby R. Banbury et\u00a0al. 2020. Benchmarking TinyML systems: Challenges and direction. arXiv preprint arXiv:2003.04821 (2020). DOI:10.48550\/arXiv.2003.04821","DOI":"10.48550\/arXiv.2003.04821"},{"key":"e_1_3_1_27_2","doi-asserted-by":"crossref","first-page":"3434","DOI":"10.1109\/SMC53992.2023.10393907","volume-title":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","author":"Barbuto Vincenzo","year":"2023","unstructured":"Vincenzo Barbuto, Claudio Savaglio, Roberto Minerva, Noel Crespi, and Giancarlo Fortino. 2023. Towards an edge intelligence-based traffic monitoring system. In 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 3434\u20133439. DOI:10.1109\/SMC53992.2023.10393907"},{"key":"e_1_3_1_28_2","first-page":"1","volume-title":"2025 International Joint Conference on Neural Networks (IJCNN)","author":"Bartoli Pietro","year":"2025","unstructured":"Pietro Bartoli et\u00a0al. 2025. Benchmarking energy and latency in TinyML: A novel method for resource-constrained AI. In 2025 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20138. DOI:10.1109\/ijcnn64981.2025.11228997"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900125"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Mohammed Djameleddine Belgoumri Mohamed Reda Bouadjenek Sunil Aryal and Hakim Hacid. 2024. Data quality in edge machine learning: A state-of-the-art survey. arXiv preprint arXiv:2406.02600 (2024). DOI:10.48550\/arXiv.2406.02600","DOI":"10.48550\/arXiv.2406.02600"},{"key":"e_1_3_1_31_2","unstructured":"Daniel J. Beutel Taner Topal Akhil Mathur Xinchi Qiu Javier Fernandez-Marques Yan Gao Lorenzo Sani Hei Li Kwing Titouan Parcollet Pedro PB de Gusm\u00e3o et\u00a0al. 2020. Flower: A friendly federated learning research framework. arXiv preprint arXiv:2007.14390 (2020)."},{"key":"e_1_3_1_32_2","first-page":"119","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Bhardwaj Romil","year":"2022","unstructured":"Romil Bhardwaj et\u00a0al. 2022. Ekya: Continuous learning of video analytics models on edge compute servers. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 119\u2013135. Retrieved from https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/bhardwaj"},{"key":"e_1_3_1_33_2","series-title":"SEC\u201923","first-page":"285","volume-title":"Proceedings of the Eighth ACM\/IEEE Symposium on Edge Computing","author":"Bhattacharjee Arpan","year":"2024","unstructured":"Arpan Bhattacharjee et\u00a0al. 2024. Poster: Edge-assisted over-the-air software updates. In Proceedings of the Eighth ACM\/IEEE Symposium on Edge Computing (Wilmington, DE, USA) (SEC\u201923). Association for Computing Machinery, New York, NY, USA, 285\u2013286. DOI:10.1145\/3583740.3628425"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544559"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Alexey Bochkovskiy Chien-Yao Wang and Hong-Yuan Mark Liao. 2020. YOLOv4: Optimal speed and accuracy of object detection. arxiv:2004.10934 [cs.CV] DOI:10.48550\/arXiv.2004.10934","DOI":"10.48550\/arXiv.2004.10934"},{"key":"e_1_3_1_36_2","volume-title":"Proceedings of the 2nd SysML Conference","author":"Bonawitz Keith","year":"2019","unstructured":"Keith Bonawitz et\u00a0al. 2019. Towards federated learning at scale: System design. In Proceedings of the 2nd SysML Conference. Retrieved from https:\/\/arxiv.org\/abs\/1902.01046"},{"key":"e_1_3_1_37_2","series-title":"MCC\u201912","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1145\/2342509.2342513","volume-title":"Proceedings of the First Edition of the MCC Workshop on Mobile Cloud Computing","author":"Bonomi Flavio","year":"2012","unstructured":"Flavio Bonomi et\u00a0al. 2012. Fog computing and its role in the internet of things. In Proceedings of the First Edition of the MCC Workshop on Mobile Cloud Computing (Helsinki, Finland) (MCC\u201912). Association for Computing Machinery, New York, NY, USA, 13\u201316. DOI:10.1145\/2342509.2342513"},{"key":"e_1_3_1_38_2","unstructured":"Siddhartha S. Borkotoky. 2025. Balancing the Energy Consumption and Latency of Over-the-Air Firmware Updates in LoRaWAN. arxiv:2508.10588 [cs.NI]. Retrieved from https:\/\/arxiv.org\/abs\/2508.10588"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30122-3_25"},{"key":"e_1_3_1_40_2","first-page":"1","volume-title":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","author":"Brandalero Marcelo","year":"2020","unstructured":"Marcelo Brandalero et\u00a0al. 2020. AITIA: Embedded AI techniques for embedded industrial applications. In 2020 International Conference on Omni-layer Intelligent Systems (COINS). 1\u20137. DOI:10.1109\/COINS49042.2020.9191672"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.33774\/coe-2025-1cnc9"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Han Cai Chuang Gan Tianzhe Wang Zhekai Zhang and Song Han. 2019. Once-for-All: Train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791 (2019). DOI:10.48550\/arXiv.1908.09791","DOI":"10.48550\/arXiv.1908.09791"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","unstructured":"Han Cai Ligeng Zhu and Song Han. 2018. ProxylessNAS: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 (2018). DOI:10.48550\/arXiv.1812.00332","DOI":"10.48550\/arXiv.1812.00332"},{"key":"e_1_3_1_45_2","article-title":"LMS vs XMSS: Comparison of stateful hash-based signature schemes on ARM cortex-M4","author":"Campos Fabio","year":"2020","unstructured":"Fabio Campos, Tim Kohlstadt, Steffen Reith, and Marc Stoettinger. 2020. LMS vs XMSS: Comparison of stateful hash-based signature schemes on ARM cortex-M4. Cryptology ePrint Archive, Paper 2020\/470. Retrieved from https:\/\/eprint.iacr.org\/2020\/470","journal-title":"Cryptology ePrint Archive, Paper 2020\/470"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-024-00928-3"},{"key":"e_1_3_1_47_2","unstructured":"CEVA Inc.2025. 2025 Edge AI Technology Report. Retrieved from https:\/\/www.ceva-ip.com\/wp-content\/uploads\/2025-Edge-AI-Technology-Report.pdf"},{"key":"e_1_3_1_48_2","unstructured":"Jiyu Chen Shuang Peng Daxiong Luo Fan Yang Renshou Wu Fangyuan Li and Xiaoxin Chen. 2025. EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices. arxiv:2503.22196 [cs.CL]. Retrieved from https:\/\/arxiv.org\/abs\/2503.22196"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_3_1_50_2","series-title":"OSDI\u201918","first-page":"579","volume-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen et\u00a0al. 2018. TVM: An automated end-to-end optimizing compiler for deep learning. In Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation (Carlsbad, CA, USA) (OSDI\u201918). USENIX Association, USA, 579\u2013594."},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.17605\/OSF.IO\/H8ERT"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/AIIoT61789.2024.10578970"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","unstructured":"Cristian Cioflan et\u00a0al. 2024. On-device domain learning for keyword spotting on low-power extreme edge embedded systems. 6\u201310. DOI:10.1109\/AICAS59952.2024.10595987","DOI":"10.1109\/AICAS59952.2024.10595987"},{"key":"e_1_3_1_54_2","unstructured":"Google Cloud. 2018. Bringing Machine Learning to the Edge with Google Cloud IoT Edge and Edge TPU. Retrieved from https:\/\/cloud.google.com\/blog\/products\/gcp\/bringing-intelligence-edge-cloud-iot."},{"key":"e_1_3_1_55_2","unstructured":"Ivan Culjak David Abram Tomislav Pribanic Hrvoje Dzapo and Mario Cifrek. 2012. A brief introduction to OpenCV. (2012) 1725\u20131730."},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.3390\/app9183885"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3067593"},{"key":"e_1_3_1_58_2","first-page":"555","volume-title":"Proceedings of the 25th International Conference on Enterprise Information Systems (ICEIS 2023) - Volume 1","author":"Santos Ricardo C. C\u00e2mara de M.","year":"2023","unstructured":"Ricardo C. C\u00e2mara de M. Santos et\u00a0al. 2023. Towards autonomous mobile inspection robots using edge AI. In Proceedings of the 25th International Conference on Enterprise Information Systems (ICEIS 2023) - Volume 1. SCITEPRESS \u2013 Science and Technology Publications, Lda, 555\u2013562. DOI:10.5220\/0011972200003467"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2984887"},{"key":"e_1_3_1_61_2","article-title":"D-STACK: High throughput DNN inference by effective multiplexing and spatio-temporal scheduling of GPUs","author":"Dhakal Aditya","year":"2024","unstructured":"Aditya Dhakal, Sameer G. Kulkarni, and K. K. Ramakrishnan. 2024. D-STACK: High throughput DNN inference by effective multiplexing and spatio-temporal scheduling of GPUs. IEEE Transactions on Cloud Computing (2024).","journal-title":"IEEE Transactions on Cloud Computing"},{"key":"e_1_3_1_62_2","unstructured":"Simone Disabato and Manuel Roveri. 2021. Tiny Machine Learning for Concept Drift. arxiv:2107.14759 [cs.LG]. Retrieved from https:\/\/arxiv.org\/abs\/2107.14759"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2024.110791"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2021.100461"},{"key":"e_1_3_1_65_2","unstructured":"Edge Impulse. 2024. Edge AI Lifecycle. Retrieved from https:\/\/docs.edgeimpulse.com\/docs\/concepts\/edge-ai-fundamentals\/edge-ai-lifecycle"},{"key":"e_1_3_1_66_2","unstructured":"Edge Impulse. 2024. Edge Impulse Documentation. Retrieved from https:\/\/docs.edgeimpulse.com\/docs"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2022.100508"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.3389\/friot.2022.1073780"},{"key":"e_1_3_1_69_2","article-title":"Welcome to the Embedded Vision Alliance!","author":"Alliance Embedded Vision","year":"2011","unstructured":"Embedded Vision Alliance. 2011. Welcome to the Embedded Vision Alliance! Blog post on Edge AI and Vision Alliance. Retrieved May 2011 from https:\/\/www.edge-ai-vision.com\/2011\/05\/welcome-to-the-embedded-vision-alliance\/","journal-title":"Blog post on Edge AI and Vision Alliance"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3134634"},{"key":"e_1_3_1_71_2","unstructured":"ETSI. 2014. Mobile-Edge Computing Initiative \u2013 Executive Briefing Issue 1. Retrieved from https:\/\/portal.etsi.org\/Portals\/0\/TBpages\/MEC\/Docs\/Mobile-edge_Computing_-_Introductory_Technical_White_Paper_V1%2018-09-14.pdf"},{"key":"e_1_3_1_72_2","unstructured":"ETSI. 2017. ETSI Multi-access Edge Computing starts second phase and renews leadership team. Retrieved from https:\/\/www.etsi.org\/newsroom\/news\/1180-2017-03-news-etsi-multi-access-edge-computing-starts-second-phase-and-renews-leadership-team"},{"key":"e_1_3_1_73_2","unstructured":"Dave Evans. 2011. The Internet of Things: How the Next Evolution of the Internet Is Changing Everything. Retrieved from https:\/\/www.cisco.com\/web\/about\/ac79\/docs\/innov\/IoT_IBSG_0411FINAL.pdf"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2951232"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","unstructured":"Samer Francy and Raghubir Singh. 2024. Edge AI: Evaluation of model compression techniques for convolutional neural networks. arXiv preprint arXiv:2409.02134 (2024). DOI:10.48550\/arXiv.2409.02134","DOI":"10.48550\/arXiv.2409.02134"},{"key":"e_1_3_1_76_2","volume-title":"NVIDIA Jetson TX1 Supercomputer-on-Module Drives Next Wave of Autonomous Machines","author":"Franklin Dustin","year":"2015","unstructured":"Dustin Franklin. 2015. NVIDIA Jetson TX1 Supercomputer-on-Module Drives Next Wave of Autonomous Machines. Retrieved October 6, 2025 from https:\/\/developer.nvidia.com\/blog\/nvidia-jetson-tx1-supercomputer-on-module-drives-next-wave-of-autonomous-machines\/"},{"key":"e_1_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.3390\/info12100425"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2971418"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1201\/9788770041027-2"},{"key":"e_1_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-025-06739-0"},{"issue":"4","key":"e_1_3_1_81_2","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1038\/scientificamerican1004-76","article-title":"The internet of things","volume":"291","author":"Gershenfeld Neil","year":"2004","unstructured":"Neil Gershenfeld, Raffi Krikorian, and Danny Cohen. 2004. The internet of things. Scientific American 291, 4 (2004), 76\u201381. Retrieved from https:\/\/fab.cba.mit.edu\/classes\/S62.12\/docs\/Cohen_Internet.pdf","journal-title":"Scientific American"},{"key":"e_1_3_1_82_2","doi-asserted-by":"publisher","unstructured":"Amir Gholami Sehoon Kim Zhen Dong Zhewei Yao Michael W. Mahoney and Kurt Keutzer. 2021. A survey of quantization methods for efficient neural network inference. arXiv preprint arXiv:2103.13630 (2021). DOI:10.48550\/arXiv.2103.13630","DOI":"10.48550\/arXiv.2103.13630"},{"key":"e_1_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630266"},{"key":"e_1_3_1_84_2","unstructured":"Google. 2021. Introducing Google Tensor. Retrieved from https:\/\/blog.google\/products\/pixel\/introducing-google-tensor\/"},{"key":"e_1_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"issue":"1","key":"e_1_3_1_86_2","article-title":"Edge-AI enabled wearable device for non-invasive type 1 diabetes detection using ECG signals","volume":"12","author":"Gragnaniello Maria","year":"2025","unstructured":"Maria Gragnaniello, Vincenzo Romano Marrazzo, Alessandro Borghese, Luca Maresca, Giovanni Breglio, and Michele Riccio. 2025. Edge-AI enabled wearable device for non-invasive type 1 diabetes detection using ECG signals. Bioengineering 12, 1 (2025). Retrieved from https:\/\/www.mdpi.com\/2306-5354\/12\/1\/4","journal-title":"Bioengineering"},{"key":"e_1_3_1_87_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13030640"},{"key":"e_1_3_1_88_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-012-0188-y"},{"key":"e_1_3_1_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA52665.2021.9647357"},{"key":"e_1_3_1_90_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2023.100848"},{"key":"e_1_3_1_91_2","doi-asserted-by":"publisher","unstructured":"Kai Han Yunhe Wang Qi Tian Jianyuan Guo Chunjing Xu and Chang Xu. 2020. GhostNet: More features from cheap operations. arXiv preprint arXiv:1911.11907 (2020). DOI:10.48550\/arXiv.1911.11907","DOI":"10.48550\/arXiv.1911.11907"},{"key":"e_1_3_1_92_2","series-title":"MOBISYS\u201924","first-page":"465","volume-title":"Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services","author":"Han Lixiang","year":"2024","unstructured":"Lixiang Han, Zimu Zhou, and Zhenjiang Li. 2024. Pantheon: Preemptible multi-DNN inference on mobile edge GPUs. In Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services (Minato-ku, Tokyo, Japan) (MOBISYS\u201924). Association for Computing Machinery, New York, NY, USA, 465\u2013478. DOI:10.1145\/3643832.3661878"},{"key":"e_1_3_1_93_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In International Conference on Learning Representations (ICLR). DOI:10.48550\/arXiv.1510.00149"},{"key":"e_1_3_1_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3105359"},{"key":"e_1_3_1_95_2","volume-title":"BenchCouncil International Symposium on Benchmarking, Measuring and Optimizing (Bench\u201918)","author":"Hao Tianshu","year":"2018","unstructured":"Tianshu Hao, Yunyou Huang, Xu Wen, Wanling Gao, Fan Zhang, Chen Zheng, Lei Wang, Hainan Ye, Kai Hwang, Zujie Ren, et\u00a0al. 2018. Edge AIBench: Towards comprehensive end-to-end edge computing benchmarking. In BenchCouncil International Symposium on Benchmarking, Measuring and Optimizing (Bench\u201918)."},{"key":"e_1_3_1_96_2","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1330257"},{"issue":"241","key":"e_1_3_1_97_2","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler Torsten","year":"2021","unstructured":"Torsten Hoefler, Dan Alistarh, Tal Ben-Nun, Nikoli Dryden, and Alexandra Peste. 2021. Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks. Journal of Machine Learning Research 22, 241 (2021), 1\u2013124. Retrieved from http:\/\/jmlr.org\/papers\/v22\/21-0366.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_98_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-025-03903-9"},{"key":"e_1_3_1_99_2","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.1109\/ICCV.2019.00140","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Howard Andrew","year":"2019","unstructured":"Andrew Howard, Mark Sandler, Bo Chen, Weijun Wang, Liang-Chieh Chen, Mingxing Tan, Grace Chu, Vijay Vasudevan, Yukun Zhu, Ruoming Pang, et\u00a0al. 2019. Searching for MobileNetV3. In 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). 1314\u20131324. DOI:10.1109\/ICCV.2019.00140"},{"key":"e_1_3_1_100_2","doi-asserted-by":"publisher","unstructured":"Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017). 10.48550\/arXiv.1704.04861","DOI":"10.48550\/arXiv.1704.04861"},{"key":"e_1_3_1_101_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12163387"},{"key":"e_1_3_1_102_2","doi-asserted-by":"publisher","unstructured":"Yang Hu Connor Imes Xuanang Zhao Souvik Kundu Peter A. Beerel Stephen P. Crago and John Paul N. Walters. 2021. Pipeline parallelism for inference on heterogeneous edge computing. arXiv preprint arXiv:2110.14895 (2021). DOI:10.48550\/arXiv.2110.14895","DOI":"10.48550\/arXiv.2110.14895"},{"key":"e_1_3_1_103_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12265-024-10504-y"},{"key":"e_1_3_1_104_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-024-01041-5"},{"key":"e_1_3_1_105_2","doi-asserted-by":"publisher","DOI":"10.1145\/3793197"},{"key":"e_1_3_1_106_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2025.3544861"},{"key":"e_1_3_1_107_2","doi-asserted-by":"publisher","unstructured":"Muhammad Hussain. 2024. YOLOv5 YOLOv8 and YOLOv10: The Go-To Detectors for Real-time Vision. arxiv:2407.02988 [cs.CV] DOI:10.48550\/arXiv.2407.02988","DOI":"10.48550\/arXiv.2407.02988"},{"key":"e_1_3_1_108_2","unstructured":"Shawn Hymel Colby Banbury Daniel Situnayake Alex Elium Carl Ward Mat Kelcey Mathijs Baaijens Mateusz Majchrzycki Jenny Plunkett David Tischler et\u00a0al. 2023. Edge Impulse: An MLOps Platform for Tiny Machine Learning. arxiv:2212.03332 [cs.DC]. Retrieved from https:\/\/arxiv.org\/abs\/2212.03332"},{"key":"e_1_3_1_109_2","doi-asserted-by":"publisher","unstructured":"Forrest N. Iandola Song Han Matthew W. Moskewicz Khalid Ashraf William J. Dally and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. arXiv preprint arXiv:1602.07360 (2016). DOI:10.48550\/arXiv.1602.07360","DOI":"10.48550\/arXiv.1602.07360"},{"key":"e_1_3_1_110_2","unstructured":"IDC. 2025. IDC Estimates Global Spending on Edge Computing to Approach $380 Billion by 2028. Retrieved from https:\/\/www.idc.com\/getdoc.jsp?containerId=prUS53261225"},{"key":"e_1_3_1_111_2","unstructured":"BrainChip Inc.2022. Akida Product Brief. Retrieved from https:\/\/brainchip.com\/wp-content\/uploads\/2022\/06\/Akida-1.0-IP-Product-Brief_final.pdf"},{"key":"e_1_3_1_112_2","unstructured":"Xilinx Inc.2023. Vitis AI Development Environment. Retrieved from https:\/\/www.xilinx.com\/products\/design-tools\/vitis\/vitis-ai.html"},{"key":"e_1_3_1_113_2","article-title":"Toolkit repository","author":"Intel OpenVINO Toolkit-Deep Learning Deployment","year":"2018","unstructured":"OpenVINO Toolkit-Deep Learning Deployment Intel. 2018. Toolkit repository. GitHub Repository (2018).","journal-title":"GitHub Repository"},{"key":"e_1_3_1_114_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110600"},{"key":"e_1_3_1_115_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2024.104268"},{"key":"e_1_3_1_116_2","first-page":"2704","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Jacob Benoit","year":"2018","unstructured":"Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, and Dmitry Kalenichenko. 2018. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2704\u20132713."},{"key":"e_1_3_1_117_2","doi-asserted-by":"publisher","unstructured":"Purvish Jajal Wenxin Jiang Arav Tewari Erik Kocinare Joseph Woo Anusha Sarraf Yung-Hsiang Lu George K. Thiruvathukal and James C. Davis. 2024. Interoperability in Deep Learning: A User Survey and Failure Analysis of ONNX Model Converters(ISSTA 2024). Association for Computing Machinery New York NY USA 1466\u20131478. DOI:10.1145\/3650212.3680374","DOI":"10.1145\/3650212.3680374"},{"key":"e_1_3_1_118_2","unstructured":"Petar Jaku\u0161 and Hrvoje D\u017eapo. 2025. Implementing keyword spotting on the MCUX947 microcontroller with integrated NPU. arXiv preprint arXiv:2506.08911 (2025). Retrieved from https:\/\/arxiv.org\/abs\/2506.08911"},{"key":"e_1_3_1_119_2","doi-asserted-by":"publisher","unstructured":"Jan Moritz Joseph Murat Sezgin Baloglu Yue Pan Rainer Leupers and Lennart Bamberg. 2021. NEWROMAP: Mapping CNNs to NoC-interconnected self-contained data-flow accelerators for edge-AI. Association for Computing Machinery New York NY USA. DOI:10.1145\/3479876.3481591","DOI":"10.1145\/3479876.3481591"},{"key":"e_1_3_1_120_2","doi-asserted-by":"publisher","DOI":"10.3390\/technologies12060081"},{"key":"e_1_3_1_121_2","doi-asserted-by":"publisher","DOI":"10.3390\/s25072243"},{"key":"e_1_3_1_122_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"e_1_3_1_123_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS56072.2025.11044227"},{"key":"e_1_3_1_124_2","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS60917.2024.10658789"},{"key":"e_1_3_1_125_2","doi-asserted-by":"publisher","unstructured":"Rahima Khanam and Muhammad Hussain. 2024. YOLOv11: An Overview of the Key Architectural Enhancements. arxiv:2410.17725 [cs.CV]. DOI:10.48550\/arXiv.2410.17725","DOI":"10.48550\/arXiv.2410.17725"},{"key":"e_1_3_1_126_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2025.104854"},{"key":"e_1_3_1_127_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.01.006"},{"key":"e_1_3_1_128_2","unstructured":"Janis Klaise Arnaud Van Looveren Clive Cox Giovanni Vacanti and Alexandru Coca. 2020. Monitoring and Explainability of Models in Production. arxiv:2007.06299 [stat.ML]. Retrieved from https:\/\/arxiv.org\/abs\/2007.06299"},{"key":"e_1_3_1_129_2","series-title":"Proceedings of Machine Learning Research","first-page":"5637","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Koh Pang Wei","year":"2021","unstructured":"Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, et\u00a0al. 2021. WILDS: A benchmark of in-the-wild distribution shifts. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 5637\u20135664. Retrieved from https:\/\/proceedings.mlr.press\/v139\/koh21a.html"},{"key":"e_1_3_1_130_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-46142-w"},{"key":"e_1_3_1_131_2","doi-asserted-by":"publisher","DOI":"10.1145\/3591268"},{"key":"e_1_3_1_132_2","doi-asserted-by":"publisher","DOI":"10.1109\/IDAP64064.2024.10711025"},{"key":"e_1_3_1_133_2","doi-asserted-by":"publisher","DOI":"10.22967\/HCIS.2022.12.053"},{"key":"e_1_3_1_134_2","doi-asserted-by":"publisher","DOI":"10.23919\/WiOpt56218.2022.9930584"},{"key":"e_1_3_1_135_2","unstructured":"Liangzhen Lai Naveen Suda and Vikas Chandra. 2018. CMSIS-NN: Efficient neural network kernels for Arm Cortex-M CPUs. arXiv preprint arXiv:1801.06601 (2018). Retrieved from https:\/\/arxiv.org\/abs\/1801.06601"},{"key":"e_1_3_1_136_2","volume-title":"Design, Automation & Test in Europe Conference & Exhibition (DATE)","author":"Lamberti Lorenzo","year":"2023","unstructured":"Lorenzo Lamberti, Luca Bompani, Victor Javier Kartsch, Manuele Rusci, Daniele Palossi, and Luca Benini. 2023. Bio-inspired autonomous exploration policies with CNN-based object detection on nano-drones. In Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE."},{"key":"e_1_3_1_137_2","unstructured":"Chris Lattner Mehdi Amini Uday Bondhugula Albert Cohen Nicolas Vasilache Tobias Grosser T. Matthew Sullivan River Riddle Yuriy O\u2019Donnell Simon Moll et\u00a0al. 2021. MLIR: A compiler infrastructure for the end of Moore\u2019s Law. arXiv preprint arXiv:2002.11054 (2021)."},{"key":"e_1_3_1_138_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00160"},{"key":"e_1_3_1_139_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10774-7"},{"key":"e_1_3_1_140_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22166097"},{"key":"e_1_3_1_141_2","doi-asserted-by":"publisher","unstructured":"Yanyu Li et\u00a0al. 2022. EfficientFormer: Vision transformers at mobilenet speed. arXiv preprint arXiv:2206.01191 (2022). DOI:10.48550\/arXiv.2206.01191","DOI":"10.48550\/arXiv.2206.01191"},{"key":"e_1_3_1_142_2","doi-asserted-by":"publisher","unstructured":"Yuhang Li Ruihao Gong Xu Tan Yang Yang Peng Hu Qi Zhang Fengwei Yu Wei Wang and Shi Gu. 2021. BRECQ: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426 (2021). DOI:10.48550\/arXiv.2102.05426","DOI":"10.48550\/arXiv.2102.05426"},{"key":"e_1_3_1_143_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.051"},{"key":"e_1_3_1_144_2","doi-asserted-by":"crossref","unstructured":"Tailin Liang Huimin Cao Sheng Sun and Jian Wu. 2021. Pruning and quantization for deep neural network acceleration: A survey. arXiv preprint arXiv:2101.09671 (2021).","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"e_1_3_1_145_2","series-title":"NIPS\u201920","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Lin Ji","year":"2020","unstructured":"Ji Lin, Wei-Ming Chen, Yujun Lin, John Cohn, Chuang Gan, and Song Han. 2020. MCUNet: Tiny deep learning on IoT devices. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS\u201920). Curran Associates Inc., Red Hook, NY, USA, Article 982, 12 pages."},{"key":"e_1_3_1_146_2","first-page":"1","volume-title":"2023 IEEE Wireless Communications and Networking Conference (WCNC)","author":"Lin Xiancheng","year":"2023","unstructured":"Xiancheng Lin, Rongkai Liu, Jiajie Xie, Qian Wei, Zhi Zhou, Xu Chen, Zhilan Huang, and Gang Lu. 2023. Online scheduling of CPU-NPU Co-inference for edge AI tasks. In 2023 IEEE Wireless Communications and Networking Conference (WCNC). 1\u20136. DOI:10.1109\/WCNC55385.2023.10118755"},{"key":"e_1_3_1_147_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23218710"},{"key":"e_1_3_1_148_2","series-title":"SenSys\u201922","first-page":"91","volume-title":"Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems","author":"Ling Neiwen","year":"2023","unstructured":"Neiwen Ling, Xuan Huang, Zhihe Zhao, Nan Guan, Zhenyu Yan, and Guoliang Xing. 2023. BlastNet: Exploiting duo-blocks for cross-processor real-time DNN inference. In Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems (Boston, Massachusetts) (SenSys\u201922). Association for Computing Machinery, New York, NY, USA, 91\u2013105. DOI:10.1145\/3560905.3568520"},{"key":"e_1_3_1_149_2","article-title":"Machine Learning for IoT Sensor Data: Enhancing Environmental Sensing with AI Algorithms","author":"Liu Hao","year":"2025","unstructured":"Hao Liu and Zhiping Ni. 2025. Machine Learning for IoT Sensor Data: Enhancing Environmental Sensing with AI Algorithms. Available at SSRN: https:\/\/ssrn.com\/abstract=5175807","journal-title":"Available at SSRN:"},{"key":"e_1_3_1_150_2","first-page":"9908","volume-title":"Advances in Neural Information Processing Systems","author":"Liu Shiwei","year":"2021","unstructured":"Shiwei Liu, Tianlong Chen, Xiaohan Chen, Zahra Atashgahi, Lu Yin, Huanyu Kou, Li Shen, Mykola Pechenizkiy, Zhangyang Wang, and Decebal Constantin Mocanu. 2021. Sparse training via boosting pruning plasticity with neuroregeneration. In Advances in Neural Information Processing Systems 34 (2021), 9908\u20139922."},{"key":"e_1_3_1_151_2","doi-asserted-by":"publisher","unstructured":"Shiwei Liu Tianlong Chen Xiaohan Chen Li Shen Decebal Constantin Mocanu Zhangyang Wang and Mykola Pechenizkiy. 2022. The unreasonable effectiveness of random pruning: Return of the most naive baseline for sparse training. arXiv preprint arXiv:2202.02643 (2022). DOI:10.48550\/arXiv.2202.02643","DOI":"10.48550\/arXiv.2202.02643"},{"key":"e_1_3_1_152_2","first-page":"1025","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Liu Yizhi","year":"2019","unstructured":"Yizhi Liu, Yao Wang, Ruofei Yu, Mu Li, Vin Sharma, and Yida Wang. 2019. Optimizing CNN model inference on CPUs. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). USENIX Association, Renton, WA, 1025\u20131040. Retrieved from https:\/\/www.usenix.org\/conference\/atc19\/presentation\/liu-yizhi"},{"key":"e_1_3_1_153_2","doi-asserted-by":"crossref","first-page":"3595","DOI":"10.1109\/CVPRW53098.2021.00399","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Lomonaco Vincenzo","year":"2021","unstructured":"Vincenzo Lomonaco et\u00a0al. 2021. Avalanche: An end-to-end library for continual learning. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 3595\u20133605. DOI:10.1109\/CVPRW53098.2021.00399"},{"key":"e_1_3_1_154_2","unstructured":"BrainChip Holdings Ltd. 2019. BrainChip Sponsors tinyML Summit and Will Demonstrate Industry-Leading Akida Neuromorphic Processor. Retrieved June 12 2025 from https:\/\/www.globenewswire.com\/news-release\/2019\/03\/05\/1748046\/0\/en\/BrainChip-Sponsors-tinyML-Summit-and-Will-Demonstrate-Industry-Leading-Akida-Neuromorphic-Processor.html"},{"key":"e_1_3_1_155_2","series-title":"CGO\u201925","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1145\/3696443.3708922","volume-title":"Proceedings of the 23rd ACM\/IEEE International Symposium on Code Generation and Optimization","author":"L\u00fccke Martin Paul","year":"2025","unstructured":"Martin Paul L\u00fccke, Oleksandr Zinenko, William S. Moses, Michel Steuwer, and Albert Cohen. 2025. The MLIR transform dialect: Your compiler is more powerful than you think. In Proceedings of the 23rd ACM\/IEEE International Symposium on Code Generation and Optimization (Las Vegas, NV, USA) (CGO\u201925). Association for Computing Machinery, New York, NY, USA, 241\u2013254. DOI:10.1145\/3696443.3708922"},{"key":"e_1_3_1_156_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-024-00620-y"},{"key":"e_1_3_1_157_2","first-page":"15941","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lv Chengtao","year":"2024","unstructured":"Chengtao Lv, Hong Chen, Jinyang Guo, Yifu Ding, and Xianglong Liu. 2024. PTQ4SAM: Post-training quantization for segment anything. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 15941\u201315951."},{"key":"e_1_3_1_158_2","unstructured":"Ningning Ma Xiangyu Zhang Hai-Tao Zheng and Jian Sun. 2018. ShuffleNet V2: Practical guidelines for efficient CNN architecture design. (2018) 116\u2013131. Retrieved from https:\/\/arxiv.org\/abs\/1807.11164"},{"key":"e_1_3_1_159_2","series-title":"Leibniz International Proceedings in Informatics (LIPIcs)","first-page":"21:1\u201321:23","volume-title":"32nd Euromicro Conference on Real-Time Systems (ECRTS 2020)","volume":"166","author":"Maggio Martina","year":"2020","unstructured":"Martina Maggio, Arne Hamann, Eckart Mayer-John, and Dirk Ziegenbein. 2020. Control-system stability under consecutive deadline misses constraints. In 32nd Euromicro Conference on Real-Time Systems (ECRTS 2020)(Leibniz International Proceedings in Informatics (LIPIcs), Vol. 166). Schloss Dagstuhl\u2013Leibniz-Zentrum f\u00fcr Informatik, 21:1\u201321:23. DOI:10.4230\/LIPIcs.ECRTS.2020.21"},{"key":"e_1_3_1_160_2","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/978-3-031-21595-7_4","volume-title":"Model and Data Engineering","author":"Mahgoub Mahmoud","year":"2023","unstructured":"Mahmoud Mahgoub, Hassan Moharram, Passent Elkafrawy, and Ahmed Awad. 2023. Benchmarking concept drift detectors for online machine learning. In Model and Data Engineering, Philippe Fournier-Viger, Ahmed Hassan, and Ladjel Bellatreche (Eds.). Springer Nature Switzerland, Cham, 43\u201357."},{"key":"e_1_3_1_161_2","first-page":"847","volume-title":"Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2025) - Volume 3: VISAPP","author":"Mahmoudi Sidi Ahmed","year":"2025","unstructured":"Sidi Ahmed Mahmoudi, Maxime Gloesener, Mohamed Benkedadra, and Jean-S\u00e9bastien Lerat. 2025. Edge AI system for real-time and explainable forest fire detection using compressed deep learning models. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2025) - Volume 3: VISAPP. SCITEPRESS \u2013 Science and Technology Publications, 847\u2013854. DOI:10.5220\/0013382500003912"},{"key":"e_1_3_1_162_2","article-title":"Standalone edge AI-based solution for tomato diseases detection","author":"Majeed Yaqoob","year":"2024","unstructured":"Yaqoob Majeed, Mike O. Ojo, and Azlan Zahid. 2024. Standalone edge AI-based solution for tomato diseases detection. SSRN Electronic Journal (2024). Preprint. Available at: https:\/\/ssrn.com\/abstract=4824801","journal-title":"SSRN Electronic Journal"},{"key":"e_1_3_1_163_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3181027"},{"key":"e_1_3_1_164_2","first-page":"18","volume-title":"Proceedings of the 14th Python in Science Conference","author":"McFee Brian","year":"2015","unstructured":"Brian McFee, Colin Raffel, Dawen Liang, Daniel P. W. Ellis, Matt McVicar, Eric Battenberg, and Oriol Nieto. 2015. Librosa: Audio and music signal analysis in Python. In Proceedings of the 14th Python in Science Conference. 18\u201325. Retrieved August 9, 2025 from https:\/\/librosa.org\/"},{"key":"e_1_3_1_165_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Mehta Sachin","year":"2022","unstructured":"Sachin Mehta and Mohammad Rastegari. 2022. MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. In Proceedings of the International Conference on Learning Representations (ICLR). DOI:10.48550\/arXiv.2110.02178"},{"key":"e_1_3_1_166_2","doi-asserted-by":"crossref","first-page":"1628","DOI":"10.21437\/Interspeech.2023-90","volume-title":"Proceedings of Interspeech 2023","author":"Michieli Umberto","year":"2023","unstructured":"Umberto Michieli, Pablo Peso Parada, and Mete Ozay. 2023. Online continual learning in keyword spotting for low-resource devices via pooling high-order temporal statistics. In Proceedings of Interspeech 2023. 1628\u20131632. DOI:10.21437\/Interspeech.2023-90"},{"key":"e_1_3_1_167_2","unstructured":"Josh Millar Yushan Huang Sarab Sethi Hamed Haddadi and Anil Madhavapeddy. 2025. Benchmarking Ultra-Low-Power \\(\\mu\\) NPUs. arxiv:2503.22567 [cs.LG]. Retrieved from https:\/\/arxiv.org\/abs\/2503.22567"},{"key":"e_1_3_1_168_2","first-page":"7454","volume-title":"2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Mittermaier Simon","year":"2020","unstructured":"Simon Mittermaier, Ludwig K\u00fcrzinger, Bernd Waschneck, and Gerhard Rigoll. 2020. Small-footprint keyword spotting on raw audio data with sinc-convolutions. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7454\u20137458."},{"key":"e_1_3_1_169_2","first-page":"1","volume-title":"2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC)","author":"Mori Yuki","year":"2025","unstructured":"Yuki Mori, Yusuke Asai, Kesuke Higashiura, Shin Katayama, Kenta Urano, Takuro Yonezawa, and Nobuo Kawaguchi. 2025. Efficient edge AI based annotation and detection framework for logistics warehouses. In 2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC). 1\u20134. DOI:10.1109\/CCNC54725.2025.10976142"},{"key":"e_1_3_1_170_2","doi-asserted-by":"publisher","DOI":"10.4236\/jdaip.2021.92006"},{"key":"e_1_3_1_171_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2024.101277"},{"key":"e_1_3_1_172_2","doi-asserted-by":"publisher","unstructured":"Markus Nagel Marios Fournarakis Rana Ali Amjad Yelysei Bondarenko Mart van Baalen and Tijmen Blankevoort. 2021. A white paper on neural network quantization. arXiv preprint arXiv:2106.08295 (2021). DOI:10.48550\/arXiv.2106.08295","DOI":"10.48550\/arXiv.2106.08295"},{"key":"e_1_3_1_173_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCASAI.2024.3453809"},{"key":"e_1_3_1_174_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2022.10.016"},{"key":"e_1_3_1_175_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13071328"},{"key":"e_1_3_1_176_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2025.200484"},{"key":"e_1_3_1_177_2","doi-asserted-by":"publisher","DOI":"10.1145\/3480172"},{"key":"e_1_3_1_178_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3075439"},{"key":"e_1_3_1_179_2","series-title":"KDD\u201922","doi-asserted-by":"crossref","first-page":"3671","DOI":"10.1145\/3534678.3539145","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Nigenda David","year":"2022","unstructured":"David Nigenda, Zohar Karnin, Muhammad Bilal Zafar, Raghu Ramesha, Alan Tan, Michele Donini, and Krishnaram Kenthapadi. 2022. Amazon SageMaker model monitor: A system for real-time insights into deployed machine learning models. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Washington DC, USA) (KDD\u201922). Association for Computing Machinery, New York, NY, USA, 3671\u20133681. DOI:10.1145\/3534678.3539145"},{"key":"e_1_3_1_180_2","doi-asserted-by":"publisher","DOI":"10.3390\/s26051535"},{"key":"e_1_3_1_181_2","first-page":"55160","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Nowak Aleksandra","year":"2023","unstructured":"Aleksandra Nowak, Bram Grooten, Decebal Constantin Mocanu, and Jacek Tabor. 2023. Fantastic weights and how to find them: Where to prune in dynamic sparse training. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 55160\u201355192. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/ad02c6f3824f871395112ae71a28eff7-Paper-Conference.pdf"},{"key":"e_1_3_1_182_2","unstructured":"NVIDIA Developer Blog. 2014. Jetson TK1: A Mobile Supercomputer for Embedded Systems. Retrieved from https:\/\/developer.nvidia.com\/blog\/jetson-tk1-mobile-embedded-supercomputer-cuda-everywhere\/"},{"key":"e_1_3_1_183_2","unstructured":"Nick O\u2019Leary and Dave Conway-Jones. 2013\u2013. Node-RED: Low-code Programming for Event-driven Applications. Retrieved August 21 2025 from https:\/\/nodered.org\/"},{"key":"e_1_3_1_184_2","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS59830.2024.10575388"},{"key":"e_1_3_1_185_2","unstructured":"OpenAI. 2022. Whisper: Speech Recognition Model. Retrieved July 28 2025 from https:\/\/github.com\/openai\/whisper"},{"key":"e_1_3_1_186_2","first-page":"444","volume-title":"Proceedings of the 28th Pan-Hellenic Conference on Progress in Computing and Informatics (PCI\u201924)","author":"Paparounas Fotios","year":"2025","unstructured":"Fotios Paparounas, Vasileios Christofas, Petros Amanatidis, Dimitris Karampatzakis, and Thomas Lagkas. 2025. Evaluating knowledge distillation and compression techniques for edge class devices. In Proceedings of the 28th Pan-Hellenic Conference on Progress in Computing and Informatics (PCI\u201924). Association for Computing Machinery, New York, NY, USA, 444\u2013449. DOI:10.1145\/3716554.3716621"},{"key":"e_1_3_1_187_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"e_1_3_1_188_2","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2024-0139"},{"key":"e_1_3_1_189_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi17060257"},{"key":"e_1_3_1_190_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3518483"},{"key":"e_1_3_1_191_2","series-title":"CF\u201923","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1145\/3587135.3592763","volume-title":"Proceedings of the 20th ACM International Conference on Computing Frontiers","author":"Petry Michael","year":"2023","unstructured":"Michael Petry, Patrick Gest, Andreas Koch, Max Ghiglione, and Martin Werner. 2023. Accelerated deep-learning inference on FPGAs in the space domain. In Proceedings of the 20th ACM International Conference on Computing Frontiers (Bologna, Italy) (CF\u201923). Association for Computing Machinery, New York, NY, USA, 222\u2013228. DOI:10.1145\/3587135.3592763"},{"key":"e_1_3_1_192_2","series-title":"MiddleWEdge\u201923","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1145\/3630180.3631201","volume-title":"Proceedings of the 2nd International Workshop on Middleware for the Edge","author":"Preuveneers Davy","year":"2023","unstructured":"Davy Preuveneers, Willem Verheyen, Sander Joos, and Wouter Joosen. 2023. On the adversarial robustness of full integer quantized TinyML models at the edge. In Proceedings of the 2nd International Workshop on Middleware for the Edge (Bologna, Italy) (MiddleWEdge\u201923). Association for Computing Machinery, New York, NY, USA, 7\u201312. DOI:10.1145\/3630180.3631201"},{"key":"e_1_3_1_193_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2024.01.016"},{"key":"e_1_3_1_194_2","unstructured":"PyTorch Developers. 2024. PyTorch Mobile: Deploying PyTorch Models on Mobile Devices. Retrieved from https:\/\/pytorch.org\/mobile\/?__hstc=114018008.2f3f33a24b44870ec4a577029c49e44b.1726790400146.1726790400147.1726790400148.1&_hssc=114018008.1.1726790400149&_hsfp=451136374"},{"key":"e_1_3_1_195_2","unstructured":"PyTorch Team. 2023. ExecuTorch: PyTorch Edge Runtime. Retrieved from https:\/\/github.com\/pytorch\/executorch"},{"key":"e_1_3_1_196_2","unstructured":"Qeexo. 2024. Qeexo AutoML Documentation. Retrieved from https:\/\/docs.qeexo.com\/guides\/userguides\/getting-started"},{"key":"e_1_3_1_197_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14132654"},{"key":"e_1_3_1_198_2","doi-asserted-by":"publisher","unstructured":"Anirudh Raju Sankaran Panchapagesan Xing Liu Arindam Mandal and Nikko Strom. 2018. Data augmentation for robust keyword spotting under playback interference. arXiv preprint arXiv:1808.00563 (2018). DOI:10.48550\/arXiv.1808.00563","DOI":"10.48550\/arXiv.1808.00563"},{"key":"e_1_3_1_199_2","first-page":"544","volume-title":"Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP","author":"Ramjattan Reshawn","year":"2023","unstructured":"Reshawn Ramjattan, Rajeev Ratan, Shiva Ramoudith, Patrick Hosein, and Daniele Mazzei. 2023. Using continual learning on edge devices for cost-effective, efficient license plate detection. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP. INSTICC, SciTePress, 544\u2013550. DOI:10.5220\/0011656300003417"},{"key":"e_1_3_1_200_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2021.11.019"},{"key":"e_1_3_1_201_2","doi-asserted-by":"publisher","DOI":"10.3390\/drones5040127"},{"key":"e_1_3_1_202_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"e_1_3_1_203_2","volume-title":"Proc. 5th MLSys Conf.","author":"Reddi V. J.","year":"2022","unstructured":"V. J. Reddi, D. Kanter, P. Mattson, J. Duke, T. Nguyen, R. Chukka, K. Shiring, K.-S. Tan, M. Charlebois, W. Chou, et\u00a0al. 2022. MLPerf mobile inference benchmark: An industry-standard open-source machine learning benchmark for on-device AI. In Proc. 5th MLSys Conf.Santa Clara, CA, USA."},{"key":"e_1_3_1_204_2","series-title":"MAPL 2018","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/3211346.3211348","volume-title":"Proceedings of the 2nd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages","author":"Roesch Jared","year":"2018","unstructured":"Jared Roesch, Steven Lyubomirsky, Logan Weber, Josh Pollock, Marisa Kirisame, Tianqi Chen, and Zachary Tatlock. 2018. Relay: A new IR for machine learning frameworks. In Proceedings of the 2nd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages (Philadelphia, PA, USA) (MAPL 2018). Association for Computing Machinery, New York, NY, USA, 58\u201368. DOI:10.1145\/3211346.3211348"},{"key":"e_1_3_1_205_2","volume-title":"Proceedings of the 21st European Conference on Computer Systems (EuroSys\u201926)","author":"Romano Diletta","year":"2026","unstructured":"Diletta Romano, Luca Mottola, and Thiemo Voigt. 2026. Neuro-C: Neural inference shaped by hardware limits. In Proceedings of the 21st European Conference on Computer Systems (EuroSys\u201926). Edinburgh, Scotland, UK."},{"key":"e_1_3_1_206_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.04.004"},{"key":"e_1_3_1_207_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2025.3587325"},{"key":"e_1_3_1_208_2","volume-title":"Proceedings of Machine Learning on the Phone and other Consumer Devices (MLPCD) Workshop at ICLR","author":"Sachs David","year":"2020","unstructured":"David Sachs, Tiezhen Wang, and Pete Warden. 2020. TensorFlow lite micro: Embedded machine learning on TinyML systems. In Proceedings of Machine Learning on the Phone and other Consumer Devices (MLPCD) Workshop at ICLR. Retrieved from https:\/\/arxiv.org\/abs\/2010.08678"},{"key":"e_1_3_1_209_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130417"},{"key":"e_1_3_1_210_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3210773"},{"key":"e_1_3_1_211_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi15050169"},{"key":"e_1_3_1_212_2","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1109\/ICSC45622.2019.8938371","volume-title":"2019 International Conference on Signal Processing and Communication (ICSC)","author":"Salau Ayodeji Olalekan","year":"2019","unstructured":"Ayodeji Olalekan Salau and Shruti Jain. 2019. Feature extraction: A survey of the types, techniques, applications. In 2019 International Conference on Signal Processing and Communication (ICSC). 158\u2013164. DOI:10.1109\/ICSC45622.2019.8938371"},{"key":"e_1_3_1_213_2","doi-asserted-by":"crossref","first-page":"4510","DOI":"10.1109\/CVPR.2018.00474","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sandler Mark","year":"2018","unstructured":"Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. MobileNetV2: Inverted residuals and linear bottlenecks. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4510\u20134520. DOI:10.1109\/CVPR.2018.00474"},{"key":"e_1_3_1_214_2","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1145\/3702468.3702479","volume-title":"Proceedings of the 2024 7th International Conference on Robot Systems and Applications (ICRSA\u201924)","author":"Sankosik Pongpanod","year":"2024","unstructured":"Pongpanod Sankosik and Chotirat Ratanamahatana. 2024. Data augmentation strategies for improving time series classification accuracy. In Proceedings of the 2024 7th International Conference on Robot Systems and Applications (ICRSA\u201924). Association for Computing Machinery, New York, NY, USA, 51\u201358. DOI:10.1145\/3702468.3702479"},{"key":"e_1_3_1_215_2","unstructured":"Ranjan Sapkota Yang Cao Konstantinos I. Roumeliotis and Manoj Karkee. 2025. Vision-Language-Action Models: Concepts Progress Applications and Challenges. arxiv:2505.04769 [cs.CV]. Retrieved from https:\/\/arxiv.org\/abs\/2505.04769"},{"key":"e_1_3_1_216_2","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1109\/ICMSCI62561.2025.10894492","volume-title":"2025 International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI)","author":"Sathiya A.","year":"2025","unstructured":"A. Sathiya, D. Angel, M. Iswarya, R. Poonkodi, Kandavalli Michael Angelo, and Nirmala Priyadharshini P. 2025. IoT enabled healthcare framework using edge AI and advanced wearable sensors for real time health monitoring. In 2025 International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI). 384\u2013392. DOI:10.1109\/ICMSCI62561.2025.10894492"},{"key":"e_1_3_1_217_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.9"},{"key":"e_1_3_1_218_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41781-024-00123-2"},{"key":"e_1_3_1_219_2","doi-asserted-by":"publisher","DOI":"10.1109\/WMCSA.1994.16"},{"key":"e_1_3_1_220_2","series-title":"NIPS\u201915","first-page":"2503","volume-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 2","author":"Sculley D.","year":"2015","unstructured":"D. Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-Francois Crespo, and Dan Dennison. 2015. Hidden technical debt in machine learning systems. In Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 2 (Montreal, Canada) (NIPS\u201915). MIT Press, Cambridge, MA, USA, 2503\u20132511."},{"key":"e_1_3_1_221_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4009388"},{"key":"e_1_3_1_222_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3175574"},{"key":"e_1_3_1_223_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"e_1_3_1_224_2","first-page":"701","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Shi Yining","year":"2023","unstructured":"Yining Shi et\u00a0al. 2023. Welder: Scheduling deep learning memory access via tile-graph. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). USENIX Association, Boston, MA, 701\u2013718. Retrieved from https:\/\/www.usenix.org\/conference\/osdi23\/presentation\/shi"},{"key":"e_1_3_1_225_2","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS60354.2023.00024"},{"key":"e_1_3_1_226_2","doi-asserted-by":"publisher","DOI":"10.1145\/3690639"},{"key":"e_1_3_1_227_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.02.004"},{"key":"e_1_3_1_228_2","first-page":"1","volume-title":"2025 IEEE 21st International Conference on Factory Communication Systems (WFCS)","author":"Sorensen Jayden Renee","year":"2025","unstructured":"Jayden Renee Sorensen, Syed Aftab Rashid, Hossam ElHussini, and Andrei-Marian Dan. 2025. Evaluating differential firmware updates for embedded IoT device fleets. In 2025 IEEE 21st International Conference on Factory Communication Systems (WFCS). 1\u20138. DOI:10.1109\/WFCS63373.2025.11077647"},{"key":"e_1_3_1_229_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06621-z"},{"key":"e_1_3_1_230_2","volume-title":"STM32 AI Model Zoo","year":"2025","unstructured":"STMicroelectronics. 2025. STM32 AI Model Zoo. Retrieved October 5, 2025 from https:\/\/github.com\/STMicroelectronics\/stm32ai-modelzoo"},{"key":"e_1_3_1_231_2","volume-title":"STM32Cube.AI \u2013 Machine Learning Toolkit for STM32 Microcontrollers","year":"2025","unstructured":"STMicroelectronics. 2025. STM32Cube.AI \u2013 Machine Learning Toolkit for STM32 Microcontrollers. Retrieved October 5, 2025 from https:\/\/stm32ai.st.com\/stm32-cube-ai\/"},{"key":"e_1_3_1_232_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2021.3133552"},{"key":"e_1_3_1_233_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23031279"},{"key":"e_1_3_1_234_2","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1109\/ICCSP64183.2025.11088699","volume-title":"2025 11th International Conference on Communication and Signal Processing (ICCSP)","author":"Swati Swati","year":"2025","unstructured":"Swati Swati et\u00a0al. 2025. Exploring quantization approaches for optimized training and inference for edge AI applications. In 2025 11th International Conference on Communication and Signal Processing (ICCSP). 1362\u20131367. DOI:10.1109\/ICCSP64183.2025.11088699"},{"key":"e_1_3_1_235_2","doi-asserted-by":"crossref","unstructured":"Hossein Taji Jos\u00e9 Miranda Miguel Pe\u00f3n-Quir\u00f3s and David Atienza. 2025. MEDEA: A Design-Time Multi-Objective Manager for Energy-Efficient DNN Inference on Heterogeneous Ultra-Low Power Platforms. arxiv:2506.19067 [cs.AR]. Retrieved from https:\/\/arxiv.org\/abs\/2506.19067","DOI":"10.1145\/3841170"},{"key":"e_1_3_1_236_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2705720"},{"key":"e_1_3_1_237_2","first-page":"2815","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, and Quoc V. Le. 2019. MnasNet: Platform-aware neural architecture search for mobile. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2815\u20132823. DOI:10.1109\/CVPR.2019.00293"},{"key":"e_1_3_1_238_2","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc V. Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (ICML). arxiv:1905.11946 [cs.LG]. Retrieved from 10.48550\/arXiv.1905.11946"},{"key":"e_1_3_1_239_2","first-page":"10778","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tan Mingxing","year":"2020","unstructured":"Mingxing Tan, Ruoming Pang, and Quoc V. Le. 2020. EfficientDet: Scalable and efficient object detection. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 10778\u201310787. DOI:10.1109\/CVPR42600.2020.01079"},{"key":"e_1_3_1_240_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3233599"},{"key":"e_1_3_1_241_2","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2025.132004"},{"key":"e_1_3_1_242_2","unstructured":"Tinygrad Contributors. 2024. Tinygrad: Open-Source Deep Learning Framework. Retrieved October 7 2025 from https:\/\/github.com\/tinygrad\/tinygrad"},{"key":"e_1_3_1_243_2","unstructured":"TinyML Deployment Working Group. 2023. Deploying TinyML Models at Scale: Insights on Monitoring and Lifecycle Management. Retrieved from https:\/\/cms.tinyml.org\/wp-content\/uploads\/ew2023\/tinyML_Deployment_WG_White_Paper_1.pdf"},{"key":"e_1_3_1_244_2","unstructured":"Maxim Tkachenko Mikhail Malyuk Andrey Holmanyuk and Nikolai Liubimov. 2020-2025. Label Studio: Data labeling software. Retrieved from https:\/\/github.com\/HumanSignal\/label-studio"},{"key":"e_1_3_1_245_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109432"},{"key":"e_1_3_1_246_2","volume-title":"Measuring Inference Performance of Machine-Learning Frameworks on Edge-class Devices with the MLMark\u2122 Benchmark","author":"Torelli Peter","unstructured":"Peter Torelli and Mohit Bangale. [n.d.]. Measuring Inference Performance of Machine-Learning Frameworks on Edge-class Devices with the MLMark\u2122 Benchmark. Technical Report. EEMBC. Retrieved from https:\/\/www.eembc.org\/techlit\/articles\/MLMARK-WHITEPAPER-FINAL-1.pdf"},{"key":"e_1_3_1_247_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"e_1_3_1_248_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708495"},{"key":"e_1_3_1_249_2","first-page":"80","volume-title":"Proceedings of the Eighth ACM\/IEEE Symposium on Edge Computing (SEC\u201923)","author":"Tu Xiaolong","year":"2024","unstructured":"Xiaolong Tu et\u00a0al. 2024. Unveiling energy efficiency in deep learning: Measurement, prediction, and scoring across edge devices. In Proceedings of the Eighth ACM\/IEEE Symposium on Edge Computing (SEC\u201923). Association for Computing Machinery, New York, NY, USA, 80\u201393. DOI:10.1145\/3583740.3628442"},{"key":"e_1_3_1_250_2","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/ICAI55435.2022.9773489","volume-title":"2022 2nd International Conference on Artificial Intelligence (ICAI)","author":"Haq Ihsan UI","year":"2022","unstructured":"Ihsan UI Haq, Rafia Mumtaz, Muhammad Talha, Zunaira Shafaq, and Muhammad Owais. 2022. Wheat rust disease classification using Edge-AI. In 2022 2nd International Conference on Artificial Intelligence (ICAI). 58\u201363. DOI:10.1109\/ICAI55435.2022.9773489"},{"key":"e_1_3_1_251_2","unstructured":"Mehmet Gorkem Ulkar and Osman Erman Okman. 2021. Ultra-low power keyword spotting at the edge. arXiv preprint arXiv:2111.04988 (2021). Retrieved from https:\/\/arxiv.org\/abs\/2111.04988"},{"key":"e_1_3_1_252_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjdhai-2025-000046"},{"key":"e_1_3_1_253_2","doi-asserted-by":"publisher","unstructured":"Ao Wang Hui Chen Lihao Liu Kai Chen Zijia Lin Jungong Han and Guiguang Ding. 2024. YOLOv10: Real-Time End-to-End Object Detection. arxiv:2405.14458 [cs.CV]. DOI:10.48550\/arXiv.2405.14458","DOI":"10.48550\/arXiv.2405.14458"},{"key":"e_1_3_1_254_2","volume-title":"Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence (AAAI\u201925\/IAAI\u201925\/EAAI\u201925)","author":"Wang Mingzi","year":"2025","unstructured":"Mingzi Wang et\u00a0al. 2025. JAQ: Joint efficient architecture design and low-bit quantization with hardware-software co-exploration. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence (AAAI\u201925\/IAAI\u201925\/EAAI\u201925). AAAI Press. DOI:10.1609\/aaai.v39i20.35415"},{"key":"e_1_3_1_255_2","doi-asserted-by":"crossref","first-page":"2519","DOI":"10.1109\/INFOCOM41043.2020.9155284","volume-title":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications","author":"Wang Shibo","year":"2020","unstructured":"Shibo Wang, Shusen Yang, and Cong Zhao. 2020. SurveilEdge: Real-time video query based on collaborative cloud-edge deep learning. In IEEE INFOCOM 2020 - IEEE Conference on Computer Communications. 2519\u20132528. DOI:10.1109\/INFOCOM41043.2020.9155284"},{"key":"e_1_3_1_256_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800286"},{"key":"e_1_3_1_257_2","doi-asserted-by":"crossref","unstructured":"Xiaobo Wang and Wei Jia. 2025. Optimizing edge AI: A comprehensive survey on data model and system strategies. arXiv preprint arXiv:2501.03265 (2025). Retrieved from https:\/\/arxiv.org\/abs\/2501.03265","DOI":"10.32388\/IZOHCH"},{"key":"e_1_3_1_258_2","doi-asserted-by":"publisher","DOI":"10.1145\/3724420"},{"key":"e_1_3_1_259_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3446585"},{"key":"e_1_3_1_260_2","unstructured":"Zi Wang Fei Wu Feng Yu Yurui Zhou Jia Hu and Geyong Min. 2024. Federated Continual Learning for Edge-AI: A Comprehensive Survey. arxiv:2411.13740 [cs.LG]. Retrieved from https:\/\/arxiv.org\/abs\/2411.13740"},{"key":"e_1_3_1_261_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI61997.2024.00021"},{"key":"e_1_3_1_262_2","doi-asserted-by":"publisher","DOI":"10.1145\/329124.329126"},{"key":"e_1_3_1_263_2","doi-asserted-by":"publisher","unstructured":"Bichen Wu et\u00a0al. 2018. FBNet: Hardware-aware efficient convnet design via differentiable neural architecture search. arXiv preprint arXiv:1812.03443 (2018). DOI:10.48550\/arXiv.1812.03443","DOI":"10.48550\/arXiv.1812.03443"},{"key":"e_1_3_1_264_2","first-page":"5627","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Wu Yuhao","year":"2024","unstructured":"Yuhao Wu et\u00a0al. 2024. Your firmware has arrived: A study of firmware update vulnerabilities. In 33rd USENIX Security Symposium (USENIX Security 24). USENIX Association, Philadelphia, PA, 5627\u20135644. Retrieved from https:\/\/www.usenix.org\/conference\/usenixsecurity24\/presentation\/wu-yuhao"},{"key":"e_1_3_1_265_2","doi-asserted-by":"publisher","unstructured":"Yirui Wu Lilai Zhang Zonghua Gu Hu Lu and Shaohua Wan. 2023. Edge-AI-driven framework with efficient mobile network design for facial expression recognition. 22 3 Article 57 (April2023) 17 pages. DOI:10.1145\/3587038","DOI":"10.1145\/3587038"},{"key":"e_1_3_1_266_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fmre.2024.01.011"},{"key":"e_1_3_1_267_2","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research)","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao et\u00a0al. 2023. SmoothQuant: Accurate and efficient post-training quantization for large language models. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research). PMLR. Retrieved from https:\/\/proceedings.mlr.press\/v202\/xiao23a.html"},{"key":"e_1_3_1_268_2","doi-asserted-by":"publisher","unstructured":"Dianlei Xu Tong Li Yong Li Xiang Su Sasu Tarkoma Tao Jiang Jon Crowcroft and Pan Hui. 2020. Edge intelligence: Architectures challenges and applications. arXiv preprint arXiv:2003.12172 (2020). DOI:10.48550\/arXiv.2003.12172","DOI":"10.48550\/arXiv.2003.12172"},{"key":"e_1_3_1_269_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2893250"},{"key":"e_1_3_1_270_2","doi-asserted-by":"crossref","DOI":"10.1109\/IPDPSW59300.2023.00128","article-title":"A lightweight concept drift detection method for on-device learning on resource-limited edge devices","author":"Yamada Takeya","year":"2023","unstructured":"Takeya Yamada and Hiroki Matsutani. 2023. A lightweight concept drift detection method for on-device learning on resource-limited edge devices. 2023 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (2023).","journal-title":"2023 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)"},{"key":"e_1_3_1_271_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.105254"},{"key":"e_1_3_1_272_2","doi-asserted-by":"publisher","unstructured":"Zhewei Yao Cheng Li Xiaoxia Wu Stephen Youn and Yuxiong He. 2023. A comprehensive study on post-training quantization for large language models. arXiv preprint arXiv:2303.08302 (2023). DOI:10.48550\/arXiv.2303.08302","DOI":"10.48550\/arXiv.2303.08302"},{"key":"e_1_3_1_273_2","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1109\/ICESC60852.2024.10690020","volume-title":"2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC)","author":"Yaragal Achyut","year":"2024","unstructured":"Achyut Yaragal and Kirankumar Bendigeri. 2024. Data aggregation in internet of things (DAIT) with edge computing. In 2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC). 472\u2013479. DOI:10.1109\/ICESC60852.2024.10690020"},{"key":"e_1_3_1_274_2","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT54382.2022.10152266"},{"key":"e_1_3_1_275_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2919760"},{"key":"e_1_3_1_276_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3042320"},{"key":"e_1_3_1_277_2","doi-asserted-by":"publisher","unstructured":"Xiangyu Zhang Xinyu Zhou Mengxiao Lin and Jian Sun. 2017. ShuffleNet: An extremely efficient convolutional neural network for mobile devices. arXiv preprint arXiv:1707.01083 (2017). DOI:10.48550\/arXiv.1707.01083","DOI":"10.48550\/arXiv.1707.01083"},{"key":"e_1_3_1_278_2","unstructured":"Yundong Zhang et\u00a0al. 2017. Hello edge: Keyword spotting on microcontrollers. arXiv preprint arXiv:1711.07128 (2017)."},{"key":"e_1_3_1_279_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3357218"},{"key":"e_1_3_1_280_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3438285"},{"key":"e_1_3_1_281_2","first-page":"1","volume-title":"2023 China Semiconductor Technology International Conference (CSTIC)","author":"Zhao Xiaotian","year":"2023","unstructured":"Xiaotian Zhao, Ruge Xu, and Xinfei Guo. 2023. Post-training quantization or quantization-aware training? that is the question. In 2023 China Semiconductor Technology International Conference (CSTIC). 1\u20133. DOI:10.1109\/CSTIC58779.2023.10219214"},{"key":"e_1_3_1_282_2","volume-title":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3 (ASPLOS\u201924)","author":"Zhao Yifan","year":"2024","unstructured":"Yifan Zhao et\u00a0al. 2024. Felix: Optimizing tensor programs with gradient descent. In Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3 (ASPLOS\u201924). Association for Computing Machinery. DOI:10.1145\/3620666.3651348"},{"key":"e_1_3_1_283_2","unstructured":"Dongqi Zheng. 2025. Diffusion Models on the Edge: Challenges Optimizations and Applications. arxiv:2504.15298 [cs.DC]. Retrieved from https:\/\/arxiv.org\/abs\/2504.15298"},{"key":"e_1_3_1_284_2","first-page":"863","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng et\u00a0al. 2020. Ansor: Generating high-performance tensor programs for deep learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 863\u2013879. Retrieved from https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/zheng"},{"key":"e_1_3_1_285_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617327"},{"key":"e_1_3_1_286_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijheatmasstransfer.2024.125188"},{"key":"e_1_3_1_287_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"issue":"6","key":"e_1_3_1_288_2","first-page":"1","article-title":"On-device training: A first overview on existing systems","volume":"20","author":"Zhu Shuai","year":"2024","unstructured":"Shuai Zhu, Thiemo Voigt, Fatemeh Rahimian, and Jeonggil Ko. 2024. On-device training: A first overview on existing systems. ACM Transactions on Sensor Networks 20, 6 (2024), 1\u201339.","journal-title":"ACM Transactions on Sensor Networks"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3827611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T10:55:25Z","timestamp":1787655325000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3827611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":287,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,30]]}},"alternative-id":["10.1145\/3827611"],"URL":"https:\/\/doi.org\/10.1145\/3827611","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]},"assertion":[{"value":"2025-10-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}