{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:46:16Z","timestamp":1770273976201,"version":"3.49.0"},"reference-count":79,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","funder":[{"name":"ARL","award":["W911NF-17-2-0196"],"award-info":[{"award-number":["W911NF-17-2-0196"]}]},{"name":"NSF","award":["CNS 20-38817"],"award-info":[{"award-number":["CNS 20-38817"]}]},{"name":"the Boeing Company, and ACE","award":["SRC JUMP 2.0 Center"],"award-info":[{"award-number":["SRC JUMP 2.0 Center"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p>\n            Pipelining deep neural networks (DNNs) across multiple Edge Tensor Processing Units (TPUs) can enhance on-device performance by increasing the capacity for DNN parameters caching and enabling pipeline parallelism. Effective deployment on pipelined Edge TPUs requires a partitioning tool to divide the DNN into segments, each assigned to a different Edge TPU in the pipeline. Achieving balanced workload distribution across these segments is crucial for optimal timing performance. However, workload balancing across Edge TPUs is challenging, as DNN execution time is influenced by proprietary hardware architecture and compiler internals, forming a black-box function inaccessible to partitioning tools. To address this challenge, this article introduces\n            <jats:italic toggle=\"yes\">SAPar<\/jats:italic>\n            , a new surrogate-assisted DNN partitioner that integrates a\n            <jats:italic toggle=\"yes\">neighborhood search engine<\/jats:italic>\n            with a\n            <jats:italic toggle=\"yes\">surrogate-assisted evaluator<\/jats:italic>\n            for effective and efficient DNN partitioning. The neighborhood search engine systematically explores the decision space, guided by knowledge obtained from empirical insights and neighborhood evaluation feedback provided by the surrogate-assisted evaluator. The evaluator cooperatively applies an\n            <jats:italic toggle=\"yes\">accurate yet time-consuming latency profiler<\/jats:italic>\n            and an\n            <jats:italic toggle=\"yes\">efficient graph transformer-based surrogate model<\/jats:italic>\n            , achieving both precision and scalability. Experiments on real Edge TPU hardware demonstrate that\n            <jats:italic toggle=\"yes\">SAPar<\/jats:italic>\n            achieves significantly better pipeline performance than Google\u2019s current profiling-based partitioner with an 8.82\u00d7 to 110\u00d7 speedup in partitioning time. Moreover,\n            <jats:italic toggle=\"yes\">SAPar<\/jats:italic>\n            reduces the bottleneck latency by 8.93% to 44.15% across five classic DNN models compared with a state-of-the-art reinforcement learning-based partitioner.\n          <\/jats:p>","DOI":"10.1145\/3761813","type":"journal-article","created":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T10:13:43Z","timestamp":1755252823000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SAPar: A Surrogate-Assisted DNN Partitioner for Efficient Inferences on Edge TPU Pipelines"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9764-6259","authenticated-orcid":false,"given":"Binqi","family":"Sun","sequence":"first","affiliation":[{"name":"Technical University of Munich","place":["Munich, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3228-7702","authenticated-orcid":false,"given":"Bohua","family":"Zou","sequence":"additional","affiliation":[{"name":"Technical University of Munich","place":["Munich, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5320-9439","authenticated-orcid":false,"given":"Yigong","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign","place":["Urbana, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0822-4976","authenticated-orcid":false,"given":"Tomasz","family":"Kloda","sequence":"additional","affiliation":[{"name":"Laboratoire d'Analyse et d'Architecture des Systemes","place":["Toulouse, France"]},{"name":"Institut National des Sciences Appliquees de Toulouse","place":["Toulouse, France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8964-6454","authenticated-orcid":false,"given":"Ling","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-7220","authenticated-orcid":false,"given":"Tarek","family":"Abdelzaher","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign","place":["Urbana, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2328-044X","authenticated-orcid":false,"given":"Marco","family":"Caccamo","sequence":"additional","affiliation":[{"name":"Technical University of Munich","place":["Munich, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"e_1_3_3_2_2","first-page":"512","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","volume":"6","author":"Akhauri Yash","year":"2024","unstructured":"Yash Akhauri and Mohamed Abdelfattah. 2024. On latency predictors for neural architecture search. In Proceedings of Machine Learning and Systems (MLSys), Vol. 6. 512\u2013523."},{"key":"e_1_3_3_3_2","volume-title":"International Conference on Automated Machine Learning (ICML)","author":"Akhauri Yash","year":"2023","unstructured":"Yash Akhauri and Mohamed S. Abdelfattah. 2023. Multi-predict: Few shot predictors for efficient neural architecture search. In International Conference on Automated Machine Learning (ICML). 23\u20131."},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00300"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi14070199"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI56018.2022.00090"},{"key":"e_1_3_3_7_2","volume-title":"Arm Ethos-U55\u2014Product Brief","author":"Ltd. Arm","year":"2024","unstructured":"Arm Ltd.2024. Arm Ethos-U55\u2014Product Brief. Arm Ltd., Cambridge, UK. Accessed: 2025-06-09."},{"key":"e_1_3_3_8_2","article-title":"AI Accelerator PCIe Card\u2014AIoT & Industrial Solutions","author":"Inc. ASUSTeK Computer","year":"2025","unstructured":"ASUSTeK Computer Inc.2025. AI Accelerator PCIe Card\u2014AIoT & Industrial Solutions. Retrieved from https:\/\/www.asus.com\/networking-iot-servers\/aiot-industrial-solutions\/gpu-edge-ai-accelerators\/ai-accelerator-pcie-card\/. (2025). Accessed: 2025-06-11.","journal-title":"https:\/\/www.asus.com\/networking-iot-servers\/aiot-industrial-solutions\/gpu-edge-ai-accelerators\/ai-accelerator-pcie-card\/"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM57271.2023.00022"},{"key":"e_1_3_3_10_2","first-page":"5:1\u20135:9","volume-title":"International Workshop on Worst-Case Execution Time Analysis (WCET)","author":"Bonenfant Armelle","year":"2017","unstructured":"Armelle Bonenfant, Denis Claraz, Marianne de Michiel, and Pascal Sotin. 2017. Early WCET prediction using machine learning. In International Workshop on Worst-Case Execution Time Analysis (WCET). 5:1\u20135:9."},{"key":"e_1_3_3_11_2","unstructured":"Bosch. 2019. Multi Purpose Camera. (2019). Retrieved from https:\/\/www.bosch-mobility.com\/media\/global\/solutions\/passenger-cars-and-light-commercial-vehicles\/driver-assistance-systems\/multi-camera-system\/multi-purpose-camera\/summary_multi-purpose-camera_en.pdfAccessed: 2025-03-19."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2018.00056"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS48715.2020.000-3"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/2584654"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_3_16_2","first-page":"2818","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Christian Szegedy","year":"2016","unstructured":"Szegedy Christian, Vanhoucke Vincent, Sergey Ioffe, Shlens Jon, and Wojna Zbigniew. 2016. Rethinking the inception architecture for computer vision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818\u20132826."},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104384"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2016.2547388"},{"key":"e_1_3_3_19_2","article-title":"M.2 Accelerator with Dual Edge TPU","year":"2025","unstructured":"Coral. 2025. M.2 Accelerator with Dual Edge TPU. Retrieved from https:\/\/coral.ai\/products\/m2-accelerator-dual-edgetpu\/. (2025). Accessed: 2025-06-11.","journal-title":"https:\/\/coral.ai\/products\/m2-accelerator-dual-edgetpu\/"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008857008151"},{"key":"e_1_3_3_21_2","volume-title":"Annual Small Satellite Conference","author":"Goodwill Justin","year":"2021","unstructured":"Justin Goodwill, Gary Crum, James MacKinnon, Cody Brewer, Michael Monaghan, Travis Wise, and Christopher Wilson. 2021. NASA spacecube edge TPU smallsat card for autonomous operations and onboard science-data analysis. In Annual Small Satellite Conference."},{"key":"e_1_3_3_22_2","article-title":"Post-training quantization","author":"Edge Google AI","year":"2024","unstructured":"Google AI Edge. 2024. Post-training quantization. Retrieved from https:\/\/ai.google.dev\/edge\/litert\/models\/post_training_quantization. (2024). Accessed: 2025-06-11.","journal-title":"https:\/\/ai.google.dev\/edge\/litert\/models\/post_training_quantization"},{"key":"e_1_3_3_23_2","article-title":"Edge TPU Compiler","author":"Research Google","year":"2025","unstructured":"Google Research. 2025. Edge TPU Compiler. Retrieved from https:\/\/coral.ai\/docs\/edgetpu\/compiler\/. (2025). Accessed: 2025-06-09.","journal-title":"https:\/\/coral.ai\/docs\/edgetpu\/compiler\/"},{"key":"e_1_3_3_24_2","article-title":"Edge TPU performance benchmarks","author":"Research Google","year":"2025","unstructured":"Google Research. 2025. Edge TPU performance benchmarks. Retrieved from https:\/\/coral.ai\/docs\/edgetpu\/benchmarks. (2025). Accessed: 2025-06-09.","journal-title":"https:\/\/coral.ai\/docs\/edgetpu\/benchmarks"},{"key":"e_1_3_3_25_2","article-title":"Pipeline a model with multiple Edge TPUs","author":"Research Google","year":"2025","unstructured":"Google Research. 2025. Pipeline a model with multiple Edge TPUs. Retrieved from https:\/\/coral.ai\/docs\/edgetpu\/pipeline\/. (2025). Accessed: 2025-06-09.","journal-title":"https:\/\/coral.ai\/docs\/edgetpu\/pipeline\/"},{"key":"e_1_3_3_26_2","article-title":"Tensorflow Model Requirements for Edge TPUs","author":"Research Google","year":"2025","unstructured":"Google Research. 2025. Tensorflow Model Requirements for Edge TPUs. Retrieved from https:\/\/coral.ai\/docs\/edgetpu\/models-intro. (2025). Accessed: 2025-06-09.","journal-title":"https:\/\/coral.ai\/docs\/edgetpu\/models-intro"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3237572"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3282307"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3520132"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops51409.2021.9431041"},{"key":"e_1_3_3_32_2","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Hsu Hung-Min","year":"2019","unstructured":"Hung-Min Hsu, Tsung-Wei Huang, Gaoang Wang, Jiarui Cai, Zhichao Lei, and Jenq-Neng Hwang. 2019. Multi-camera tracking of vehicles based on deep features Re-ID and trajectory-based camera link models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops."},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae088"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC53511.2021.00014"},{"key":"e_1_3_3_36_2","article-title":"IEI Mustang\u2011T100\u2011T5 AI Accelerator Card with Google Coral Edge TPU","author":"Corp. IEI Integration","year":"2021","unstructured":"IEI Integration Corp.2021. IEI Mustang\u2011T100\u2011T5 AI Accelerator Card with Google Coral Edge TPU. Retrieved from https:\/\/www.bvm.co.uk\/news\/iei-mustang-t100-t5-coral-edge-tpu. (2021). Accessed: 2025-06-11.","journal-title":"https:\/\/www.bvm.co.uk\/news\/iei-mustang-t100-t5-coral-edge-tpu"},{"key":"e_1_3_3_37_2","volume-title":"Intel Vision Accelerator Design with Intel Movidius VPUs: HAL Configuration Guide","author":"Corporation Intel","year":"2019","unstructured":"Intel Corporation. 2019. Intel Vision Accelerator Design with Intel Movidius VPUs: HAL Configuration Guide. Intel Corporation, Santa Clara, CA. Revision 1.3; accessed 2025-06-09."},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00033"},{"key":"e_1_3_3_39_2","first-page":"18015","article-title":"\\(S^{3}\\) : Increasing GPU utilization during generative inference for higher throughput","volume":"36","author":"Jin Yunho","year":"2023","unstructured":"Yunho Jin, Chun-Feng Wu, David Brooks, and Gu-Yeon Wei. 2023. \\(S^{3}\\) : Increasing GPU utilization during generative inference for higher throughput. Advances in Neural Information Processing Systems (NeurIPS) 36 (2023), 18015\u201318027. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/3a13be0c5dae69e0f08065f113fb10b8-Paper-Conference.pdf","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/368996.369025"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT58117.2023.00018"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.1982.1653825"},{"key":"e_1_3_3_44_2","first-page":"27016","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Lee Hayeon","year":"2021","unstructured":"Hayeon Lee, Sewoong Lee, Song Chong, and Sung Ju Hwang. 2021. Hardware-adaptive efficient latency prediction for NAS via meta-learning. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 34. 27016\u201327028."},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM52596.2021.9652907"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3043716"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3323212"},{"key":"e_1_3_3_48_2","first-page":"66","volume-title":"Drone Systems Engineering and Rapid Simulation and Performance Evaluation: Methods and Tools Proceedings","author":"Menard Christian","year":"2021","unstructured":"Christian Menard, Andr\u00e9s Goens, Gerald Hempel, Robert Khasanov, Julian Robledo, Felix Teweleitt, and Jeronimo Castrillon. 2021. Mocasin\u2013rapid prototyping of rapid prototyping tools: A framework for exploring new approaches in mapping software to heterogeneous multi-cores. In Drone Systems Engineering and Rapid Simulation and Performance Evaluation: Methods and Tools Proceedings. 66\u201373."},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774764"},{"key":"e_1_3_3_50_2","article-title":"Working with DLA\u2014Sparsity on DLA","author":"Corporation NVIDIA","year":"2025","unstructured":"NVIDIA Corporation. 2025. Working with DLA\u2014Sparsity on DLA. Retrieved from https:\/\/docs.nvidia.com\/deeplearning\/tensorrt\/latest\/inference-library\/work-with-dla.html#sparsity-on-dla. (2025). Last updated: May 21, 2025; Accessed: 2025-06-09.","journal-title":"https:\/\/docs.nvidia.com\/deeplearning\/tensorrt\/latest\/inference-library\/work-with-dla.html#sparsity-on-dla"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITNAC55475.2022.9998427"},{"issue":"3","key":"e_1_3_3_52_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3698767","article-title":"Early-exit deep neural network-a comprehensive survey","volume":"57","author":"P. Haseena Rahmath","year":"2024","unstructured":"Haseena Rahmath P., Vishal Srivastava, Kuldeep Chaurasia, Roberto G. Pacheco, and Rodrigo S. Couto. 2024. Early-exit deep neural network-a comprehensive survey. Comput. Surveys 57, 3 (2024), 1\u201337.","journal-title":"Comput. Surveys"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS58335.2023.00036"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.02.036"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2004.07.022"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC55918.2022.00017"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/1132357.1132364"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3033730"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/HI-POCT54491.2022.9744071"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370309"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS61025.2024.00028"},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS58335.2023.00019"},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3529218"},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655979"},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-020-00166-z"},{"key":"e_1_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"e_1_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2019.8926767"},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/PDP59025.2023.00020"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06605-9"},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3092181"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.03.018"},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247706"},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEC54971.2022.00023"},{"key":"e_1_3_3_75_2","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying Chengxuan","year":"2021","unstructured":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. 2021. Do transformers really perform badly for graph representation? Advances in Neural Information Processing Systems (NeurIPS) 34 (2021), 28877\u201328888. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/f1c1592588411002af340cbaedd6fc33-Paper.pdf","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_3_76_2","first-page":"7105","volume-title":"International Conference on Machine Learning (ICML)","author":"Ying Chris","year":"2019","unstructured":"Chris Ying, Aaron Klein, Eric Christiansen, Esteban Real, Kevin Murphy, and Frank Hutter. 2019. Nas-bench-101: Towards reproducible neural architecture search. In International Conference on Machine Learning (ICML). 7105\u20137114."},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00940"},{"key":"e_1_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3615740"},{"key":"e_1_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2023.104336"},{"key":"e_1_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM61039.2024.10773756"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3761813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T14:28:18Z","timestamp":1759933698000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3761813"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":79,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1145\/3761813"],"URL":"https:\/\/doi.org\/10.1145\/3761813","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,26]]},"assertion":[{"value":"2025-08-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}