{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:20:38Z","timestamp":1781194838511,"version":"3.54.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014440","name":"Spanish Government MICINN","doi-asserted-by":"publisher","award":["RTI2018-097088-B-C31"],"award-info":[{"award-number":["RTI2018-097088-B-C31"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union H2020 MSCA through project ACHIEVE-ITN","award":["765866"],"award-info":[{"award-number":["765866"]}]},{"DOI":"10.13039\/100000006","name":"U.S. Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-19-1-2156"],"award-info":[{"award-number":["N00014-19-1-2156"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/jiot.2020.2981684","type":"journal-article","created":{"date-parts":[[2020,3,18]],"date-time":"2020-03-18T22:10:50Z","timestamp":1584569450000},"page":"9227-9240","source":"Crossref","is-referenced-by-count":30,"title":["PreVIous: A Methodology for Prediction of Visual Inference Performance on IoT Devices"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3487-1712","authenticated-orcid":false,"given":"Delia","family":"Velasco-Montero","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0476-4676","authenticated-orcid":false,"given":"Jorge","family":"Fernandez-Berni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4230-3988","authenticated-orcid":false,"given":"Ricardo","family":"Carmona-Galan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1006-5241","authenticated-orcid":false,"given":"Angel","family":"Rodriguez-Vazquez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Overview of the Internet of Things","year":"2012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2683200"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2017.2745818"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2869929"},{"key":"ref7","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \u00a11MB model size","author":"Iandola","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00215"},{"key":"ref9","article-title":"SqueezeDet: Unified, small, low power fully convolutional neural networks for real-time object detection for autonomous driving","author":"Wu","year":"2016"},{"key":"ref10","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref11","article-title":"Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation","author":"Sandler","year":"2018"},{"key":"ref12","article-title":"ShuffleNet: An extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2017"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01264-9_8","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","author":"Ma","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.76"},{"key":"ref16","article-title":"An analysis of deep neural network models for practical applications","author":"Canziani","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877890"},{"key":"ref19","article-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning","author":"Wang","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref21","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016"},{"key":"ref22","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or \u22121","author":"Courbariaux","year":"2016"},{"key":"ref23","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhou"},{"key":"ref24","first-page":"1","article-title":"Pruning convolutional neural networks for resource efficient transfer learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Molchanov"},{"key":"ref25","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2018.01.036"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref29","article-title":"Fast training of convolutional networks through FFTs","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Mathieu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11179-7_36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451339"},{"key":"ref32","article-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","author":"Kim","year":"2015"},{"key":"ref33","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lebedev"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref37","article-title":"Design automation for efficient deep learning computing","author":"Han","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00171"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-46147-8_29"},{"key":"ref42","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Cai"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"ref44","first-page":"19","article-title":"HyperPower: Power- and memory-constrained hyper-parameter optimization for neural networks","volume-title":"Proc. Design Autom. Test Europe Conf. Exhibit. (DATE)","author":"Stamoulis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref46","first-page":"6071","article-title":"Designing energy-efficient convolutional neural networks using energy-aware pruning","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Yang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2946538"},{"key":"ref49","article-title":"NeuralPower: Predict and deploy energy-efficient convolutional neural networks","author":"Cai","year":"2017"},{"key":"ref50","article-title":"Fine-grained energy profiling for deep convolutional neural networks on the Jetson TX1","author":"Rodrigues","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3229556.3229562"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3194554.3194565"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CAHPC.2018.8645908"},{"key":"ref55","article-title":"Paleo: A performance model for deep neural networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Qi"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.007"},{"key":"ref57","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Ioffe"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref63","volume-title":"Automatically Tuned Linear Algebra Software (ATLAS)","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref65","volume-title":"Intel Math Kernel Library","year":"2020"},{"key":"ref66","volume-title":"Dense Linear Algebra on GPUs","year":"2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref68","volume-title":"Raspberry Pi 3 Model B","year":"2020"},{"key":"ref69","volume-title":"OpenCV","year":"2020"},{"key":"ref70","volume-title":"Odroid XU4","year":"2020"},{"key":"ref71","article-title":"Striving for simplicity: The All Convolutional Net","author":"Springenberg","year":"2014"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref73","volume-title":"PreVIous. Github Repository","author":"Velasco-Montero","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref75","volume-title":"The CIFAR Dataset","author":"Krizhevsky","year":"2020"},{"key":"ref76","volume-title":"The MNIST Database of Handwritten Digits","author":"LeCun","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref78","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Krizhevsky"},{"key":"ref79","article-title":"Lets keep it simple, using simple architectures to outperform deeper and more complex architectures","author":"Hasanpour","year":"2016"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11876"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9219268\/09040398.pdf?arnumber=9040398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:47:23Z","timestamp":1706060843000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9040398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":82,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2020.2981684","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}