{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T23:54:54Z","timestamp":1773014094037,"version":"3.50.1"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T00:00:00Z","timestamp":1644278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"European Union\u2019s Horizon 2020 Research and Innovation program","award":["780788"],"award-info":[{"award-number":["780788"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2022,3,31]]},"abstract":"<jats:p>Convolutional Neural Networks (CNNs) are biologically inspired computational models that are at the heart of many modern computer vision and natural language processing applications. Some of the CNN-based applications are executed on mobile and embedded devices. Execution of CNNs on such devices places numerous demands on the CNNs, such as high accuracy, high throughput, low memory cost, and low energy consumption. These requirements are very difficult to satisfy at the same time, so CNN execution at the edge typically involves trade-offs (e.g., high CNN throughput is achieved at the cost of decreased CNN accuracy). In existing methodologies, such trade-offs are either chosen once and remain unchanged during a CNN-based application execution, or are adapted to the properties of the CNN input data. However, the application needs can also be significantly affected by the changes in the application environment, such as a change of the battery level in the edge device. Thus, CNN-based applications need a mechanism that allows to dynamically adapt their characteristics to the changes in the application environment at run-time. Therefore, in this article, we propose a scenario-based run-time switching (SBRS) methodology, that implements such a mechanism.<\/jats:p>","DOI":"10.1145\/3488718","type":"journal-article","created":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T15:11:51Z","timestamp":1644333111000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Scenario Based Run-Time Switching for Adaptive CNN-Based Applications at the Edge"],"prefix":"10.1145","volume":"21","author":[{"given":"Svetlana","family":"Minakova","sequence":"first","affiliation":[{"name":"Leiden University, Leiden, South Holland, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dolly","family":"Sapra","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, North Holland, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todor","family":"Stefanov","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, South Holland, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andy D.","family":"Pimentel","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, North Holland, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,2,8]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.2016.29"},{"key":"e_1_3_2_3_2","unstructured":"Brandon Reagen Udit Gupta Robert Adolf Michael M. Mitzenmacher Alexander M. Rush Gu-Yeon Wei and David Brooks.2018. Weightless: Lossy weight encoding for deep neural network compression. In Proceedings of the 35th International Conference on Machine Learning ."},{"key":"e_1_3_2_4_2","unstructured":"Chi-Hung Hsu Shu-Huan Chang Da-Cheng Juan Jia-Yu Pan Yu-Ting Chen Wei Wei and Shih-Chieh Chang.2018. MONAS: Multi-objective neural architecture search using reinforcement learning. arXiv:1806.10332v2. Retrieved from https:\/\/arxiv.org\/abs\/1806.10332."},{"key":"e_1_3_2_5_2","article-title":"Keras","author":"Chollet Fran\u00e7ois","year":"2015","unstructured":"Fran\u00e7ois Chollet. 2015. Keras. Retrieved April 2, 2021 from https:\/\/keras.io.","journal-title":"https:\/\/keras.io"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3243494"},{"key":"e_1_3_2_7_2","unstructured":"http:\/\/www.cs.toronto.edu\/ kriz\/cifar.html. 2013 CIFAR-10 (Canadian Institute for Advanced Research)"},{"key":"e_1_3_2_8_2","first-page":"10734","volume-title":"Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Jia. Bichen Wu, Kurt Keutzer, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, and Yangqing","year":"2019","unstructured":"Bichen Wu, Kurt Keutzer, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, and Yangqing Jia.2019. FBNet: Hardware-aware efficient ConvNet design via differentiable neural architecture search. In Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Computer Vision Foundation\/IEEE, 10734\u201310742. DOI:DOI:https:\/\/doi.org\/10.1109\/CVPR.2019.01099"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400286.3418245"},{"key":"e_1_3_2_10_2","first-page":"967","volume-title":"Proceedings of the 2018 Design, Automation & Test in Europe Conference & Exhibition","author":"Bouganis. Christos Kyrkou, George Plastiras, Theo Theocharides, Stylianos I. Venieris, and Christos","year":"2018","unstructured":"Christos Kyrkou, George Plastiras, Theo Theocharides, Stylianos I. Venieris, and Christos Bouganis.2018. DroNet: Efficient convolutional neural network detector for real-time UAV applications. In Proceedings of the 2018 Design, Automation & Test in Europe Conference & Exhibition. 967\u2013972. DOI:DOI:https:\/\/doi.org\/10.23919\/DATE.2018.8342149"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Fernando Moya Rueda Gernot Fink Rene Grzeszick Sascha Feldhorst and Michael Ten Hompel.2018. Convolutional neural networks for human activity recognition using body-worn sensors. Informatics 5 2 (2018) 26.","DOI":"10.3390\/informatics5020026"},{"key":"e_1_3_2_12_2","unstructured":"https:\/\/github.com\/gaohuang\/MSDNet 2018 MSDNet Code"},{"key":"e_1_3_2_13_2","unstructured":"In Proceedings of the International Conference on Learning Representations 2018 Multi-scale dense networks for resource efficient image classification"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242044"},{"key":"e_1_3_2_15_2","unstructured":"Ilias Theodorakopoulos Vasileios K. Pothos Dimitrios Kastaniotis and Nikos Fragoulis.2017. Parsimonious inference on convolutional neural networks: Learning and applying on-line kernel activation rules. arXiv:1701.05221v5. Retrieved from https:\/\/arxiv.org\/abs\/1701.05221."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3012391"},{"key":"e_1_3_2_17_2","article-title":"Slimmable neural networks","author":"Yang. Jiahui Yu, Linjie Yang, Ning Xu, and Jianchao","year":"2019","unstructured":"Jiahui Yu, Linjie Yang, Ning Xu, and Jianchao Yang.2019. Slimmable neural networks. In Proceedings of the International Conference on Learning Representations.","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"e_1_3_2_19_2","volume-title":"Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition","author":"Sun. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun.2016. Deep residual learning for image recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. DOI:DOI:https:\/\/doi.org\/10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3088525.3088527"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_8"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/3437539.3437731"},{"key":"e_1_3_2_23_2","unstructured":"Md Zahangir Alom Tarek M. Taha Christopher Yakopcic Stefan Westberg Mahmudul Hasan Brian C. Van Esesn Abdul Awwal and Vijayan K. Asari.2018. The history began from AlexNet: A comprehensive survey on deep learning approaches. arXiv:1803.01164v2. Retrieved from https:\/\/arxiv.org\/abs\/1803.01164."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342997"},{"issue":"11","key":"e_1_3_2_25_2","article-title":"Machine learning in resource-scarce embedded systems, FPGAs, and end-devices: A survey","volume":"8","author":"Cabral. Sergio Branco, Andre G. Ferreira, and Jorge","year":"2019","unstructured":"Sergio Branco, Andre G. Ferreira, and Jorge Cabral.2019. Machine learning in resource-scarce embedded systems, FPGAs, and end-devices: A survey. Electronics 8, 11 (2019), 1289. DOI:DOI:https:\/\/doi.org\/10.3390\/electronics8111289","journal-title":"Electronics"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305436"},{"key":"e_1_3_2_27_2","first-page":"7","volume-title":"Proceedings of the 2018 4th International Conference on Green Technology and Sustainable Development","author":"Le. Truong-Dong Do, Minh-Thien Duong, Quoc-Vu Dang, and My-Ha","year":"2018","unstructured":"Truong-Dong Do, Minh-Thien Duong, Quoc-Vu Dang, and My-Ha Le.2018. Real-time self-driving car navigation using deep neural network. In Proceedings of the 2018 4th International Conference on Green Technology and Sustainable Development. 7\u201312."},{"key":"e_1_3_2_28_2","article-title":"Designing energy-efficient convolutional neural networks using energy-aware pruning","author":"al. Tien-Ju Yang et","year":"2017","unstructured":"Tien-Ju Yang et al.2017. Designing energy-efficient convolutional neural networks using energy-aware pruning. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition.","journal-title":"Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317757"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"e_1_3_2_31_2","article-title":"Deep learning","author":"Hinton. Yann LeCun, Yoshua Bengio, and Geoffrey","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton.2015. Deep learning. Nature 521, 7553 (2015), 436\u2013444.","journal-title":"Nature"},{"key":"e_1_3_2_32_2","article-title":"Dual dynamic inference: Enabling more efficient, adaptive and controllable deep inference","author":"Lin. Yue Wang, Jianghao Shen, Ting-Kuei Hu, Pengfei Xu, Tan Nguyen, Richard Baraniuk, Zhangyang Wang, and Yingyan","year":"2020","unstructured":"Yue Wang, Jianghao Shen, Ting-Kuei Hu, Pengfei Xu, Tan Nguyen, Richard Baraniuk, Zhangyang Wang, and Yingyan Lin.2020. Dual dynamic inference: Enabling more efficient, adaptive and controllable deep inference. IEEE Journal of Selected Topics in Signal Processing 14, 4 (2020), 623\u2013633.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"e_1_3_2_33_2","unstructured":"Yhui Xu Lingxi Xie Xiaopeng Zhang Xin Chen Bowen Shi Qi Tian and Hongkai Xiong.2020. Latency-aware differentiable neural architecture search. arXiv:2001.06392v2. Retrieved from https:\/\/arxiv.org\/abs\/2001.06392."},{"key":"e_1_3_2_34_2","volume-title":"Proceedings of the Systems Modeling Language","author":"Lai Liangzhen","year":"2018","unstructured":"Liangzhen Lai, Naveen Suda, and Vikas Chandra. 2018. Not all ops are created equal! In Proceedings of the Systems Modeling Language."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504485"},{"key":"e_1_3_2_36_2","volume-title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","author":"Le. Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, and Quoc V.","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 Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_37_2","volume-title":"Temporal Analysis and Scheduling of Hard Real-Time Radios Running on a Multi-Processor","author":"Moreira Orlando","year":"2012","unstructured":"Orlando Moreira. 2012. Temporal Analysis and Scheduling of Hard Real-Time Radios Running on a Multi-Processor. Ph.D. Dissertation. Technical University Eindhoven."},{"key":"e_1_3_2_38_2","article-title":"Jetson TX2","year":"2016","unstructured":"NVIDIA. 2016. Jetson TX2. Retrieved July 23, 2020 from https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-tx2.","journal-title":"https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-tx2"},{"key":"e_1_3_2_39_2","article-title":"Tensorrt Framework","year":"2021","unstructured":"NVIDIA. 2021. Tensorrt Framework. Retrieved August 5, 2020 from https:\/\/developer.nvidia.com\/tensorrt.","journal-title":"https:\/\/developer.nvidia.com\/tensorrt"},{"key":"e_1_3_2_40_2","first-page":"532","volume-title":"Cross-Validation","author":"Refaeilzadeh Payam","year":"2009","unstructured":"Payam Refaeilzadeh, Lei Tang, and Huan Liu. 2009. Cross-Validation. Springer US, 532\u2013538."},{"key":"e_1_3_2_41_2","author":"Reiss Attila","year":"2012","unstructured":"Attila Reiss. 2012. Retrieved August 5, 2020 from https:\/\/archive.ics.uci.edu\/ml\/datasets\/PAMAP2PhysicalActivityMonitoring.","journal-title":"https:\/\/archive.ics.uci.edu\/ml\/datasets\/PAMAP2PhysicalActivityMonitoring"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2007.4424990"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-55789-8_61"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.3390\/a12080154"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858365"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488718","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:13Z","timestamp":1750188673000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,8]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,3,31]]}},"alternative-id":["10.1145\/3488718"],"URL":"https:\/\/doi.org\/10.1145\/3488718","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,8]]},"assertion":[{"value":"2021-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}