{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T22:44:43Z","timestamp":1781131483493,"version":"3.54.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100007136","name":"Secretar\u00eda de Estado de Investigaci\u00f3n, Desarrollo e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["TEC2015-66878-C3-1-R"],"award-info":[{"award-number":["TEC2015-66878-C3-1-R"]}],"id":[{"id":"10.13039\/501100007136","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006461","name":"Agencia de Innovaci\u00f3n y Desarrollo de Andaluc\u00eda","doi-asserted-by":"publisher","award":["TIC 2338-2013"],"award-info":[{"award-number":["TIC 2338-2013"]}],"id":[{"id":"10.13039\/501100006461","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["765866"],"award-info":[{"award-number":["765866"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2869929","type":"journal-article","created":{"date-parts":[[2018,9,12]],"date-time":"2018-09-12T18:54:38Z","timestamp":1536778478000},"page":"51680-51692","source":"Crossref","is-referenced-by-count":23,"title":["Optimum Selection of DNN Model and Framework for Edge Inference"],"prefix":"10.1109","volume":"6","author":[{"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"}]},{"given":"Ricardo","family":"Carmona-Galan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angel","family":"Rodriguez-Vazquez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","year":"2018","journal-title":"Netscope CNN Analyzer"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","author":"he","year":"2015","journal-title":"Deep residual learning for image recognition"},{"key":"ref32","author":"szegedy","year":"2016","journal-title":"Inception-v4 inception-resnet and the impact of residual connections on learning"},{"key":"ref31","author":"szegedy","year":"2014","journal-title":"Going Deeper with Convolutions"},{"key":"ref30","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref37","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref36","author":"hasanpour","year":"2016","journal-title":"Lets keep it simple using simple architectures to outperform deeper and more complex architectures"},{"key":"ref35","author":"howard","year":"2017","journal-title":"Mobilenets Efficient convolutional neural networks for mobile vision applications"},{"key":"ref34","author":"iandola","year":"2016","journal-title":"SqueezeNet Alexnet-level accuracy with $50\\times$ fewer parameters and"},{"key":"ref28","year":"2018","journal-title":"Caffe to Caffe2"},{"key":"ref27","year":"2018","journal-title":"Model zoo"},{"key":"ref29","author":"lin","year":"2013","journal-title":"Network in Network"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2017.2745818"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref20","year":"2018","journal-title":"Optimized BLAS Library Based on GotoBLAS2 1 13 BSD Version"},{"key":"ref22","year":"2017","journal-title":"A Docker Image for Tensorflow"},{"key":"ref21","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref24","year":"2018","journal-title":"Opencv"},{"key":"ref23","year":"2018","journal-title":"TensorFlow-Slim Image Classification Library"},{"key":"ref26","year":"2018","journal-title":"Caffe Framework"},{"key":"ref25","year":"2018","journal-title":"Open Source Computer Vision Library"},{"key":"ref50","year":"0","journal-title":"BVLC googlenet"},{"key":"ref51","year":"2018","journal-title":"SqueezeNet"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CCBD.2016.029"},{"key":"ref11","author":"canziani","year":"2017","journal-title":"An analysis of deep neural network models for practical applications"},{"key":"ref40","year":"2017","journal-title":"Caffe to TensorFlow"},{"key":"ref12","article-title":"CS341 final report: Towards real-time detection and camera triggering","author":"zhang","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2017.05.033"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.10.055"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISORC.2016.14"},{"key":"ref16","first-page":"1","article-title":"Deep learning on a raspberry Pi for real time face recognition","author":"d\u00fcrr","year":"2015","journal-title":"Proc EUROGRAPH"},{"key":"ref17","first-page":"1","article-title":"Benchmarking of CNNs for low-cost, low-power robotics applications","author":"pena","year":"2017","journal-title":"Proc New Frontiers Deep Learn Robot Workshop RSS"},{"key":"ref18","year":"2018","journal-title":"Raspbian"},{"key":"ref19","author":"jia","year":"2014","journal-title":"Caffe Convolutional Architecture for Fast Feature Embedding"},{"key":"ref4","first-page":"444","article-title":"Towards closing the energy gap between HOG and CNN features for embedded vision","author":"suleiman","year":"2017","journal-title":"Proc IEEE Int Symp Circuits Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2017.2745798"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref5","year":"2016","journal-title":"Emerging Vision Technologies Enabling a New Era of Intelligent Devices"},{"key":"ref8","first-page":"99","article-title":"Deep learning with theano, torch, caffe, tensorflow, and deeplearning4J: Which one is the best in speed and accuracy?","author":"kovalev","year":"2016","journal-title":"Proc Int Conf Pattern Recognit Inf Process"},{"key":"ref7","year":"2016","journal-title":"Raspberry Pi 3 Model B"},{"key":"ref49","year":"2018","journal-title":"MobileNet_v1_1 0_224"},{"key":"ref9","author":"bahrampour","year":"2015","journal-title":"Comparative study of caffe neon theano and torch for deep learning"},{"key":"ref46","year":"2018","journal-title":"SimpleNet"},{"key":"ref45","year":"2018","journal-title":"Caffe Implementation of Google’s MobileNets (V1 and V2)"},{"key":"ref48","year":"2016","journal-title":"ResNet V1 50"},{"key":"ref47","year":"2016","journal-title":"Inception V1"},{"key":"ref42","year":"2017","journal-title":"BAIR\/BVLC GoogLeNet Model"},{"key":"ref41","year":"2018","journal-title":"Model Zoo Network in Network Model"},{"key":"ref44","year":"2016","journal-title":"SqueezeNet_v1 1"},{"key":"ref43","year":"2016","journal-title":"Deep residual learning for image recognition"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08463447.pdf?arnumber=8463447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:15:16Z","timestamp":1642004116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8463447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2869929","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}