{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T14:09:55Z","timestamp":1762956595750,"version":"3.41.2"},"reference-count":31,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T00:00:00Z","timestamp":1617667200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Trans Emerging Tel Tech"],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>As the rapid evolution of smart devices and real\u2010time applications, many new kinds of computation\u2010intensive services have been emerged successively and the corresponding requirements have been growing dramatically. Extended from cloud computing, mobile edge computing (MEC) is a novel technology which can provide powerful computing resource at the proximity of resource\u2010restrained mobile devices. Thus, it enables collaboration between edge server and mobile device, which can improve the quality of experience for users. In this article, we propose an intelligent collaborative inference (ICI) approach for real\u2010time computation\u2010intensive services in MEC network, which can achieve intelligent service partitioning and partial task offloading. Since machine learning algorithms have been applied in many applications with the advancement of big data and computing power, we focus on the services based on deep\u2010learning. Particularly, we research a service based on Pose\u2010Net model to achieve human pose estimation in the field of computer vision. And we design relevant ICI algorithm to achieve fine\u2010grained video stream processing in consideration of video service requirement, deep neural network (DNN) model structure, mobile device capability, wireless network condition, and cooperative server workload. Based on Python programming language and TensorFlow library, we test the ICI approach with some practical simulation parameters on real hardware platforms. The experiment results show that the presented ICI approach have superior performance in terms of service frame rate and client energy consumption than other benchmark approaches.<\/jats:p>","DOI":"10.1002\/ett.4263","type":"journal-article","created":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T11:09:00Z","timestamp":1617707340000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["An intelligent collaborative inference approach of service partitioning and task offloading for deep learning based service in mobile edge computing networks"],"prefix":"10.1002","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0254-141X","authenticated-orcid":false,"given":"Xuejing","family":"Li","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Next Generation Internet Interconnection Devices Beijing Jiaotong University  Beijing China"}]},{"given":"Yajuan","family":"Qin","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Next Generation Internet Interconnection Devices Beijing Jiaotong University  Beijing China"}]},{"given":"Huachun","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Next Generation Internet Interconnection Devices Beijing Jiaotong University  Beijing China"}]},{"given":"Zhewei","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Third Research Laboratory Institute of Information Engineering, Chinese Academy of Sciences  Beijing China"}]}],"member":"311","published-online":{"date-parts":[[2021,4,6]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"crossref","unstructured":"HalpernM ZhuY ReddiVJ. Mobile CPU's rise to power: quantifying the impact of generational mobile CPU design trends on performance energy and user satisfaction;2016.","DOI":"10.1109\/HPCA.2016.7446054"},{"volume-title":"A Survey on Resource Scheduling in Cloud Computing: Issues and Challenges","year":"2016","author":"Singh S","key":"e_1_2_11_3_1"},{"issue":"1","key":"e_1_2_11_4_1","first-page":"450","article-title":"Mobile edge computing: a survey","volume":"5","author":"Abbas N","year":"2018","journal-title":"IEEE IoT J"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2487344"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2785305"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2922362"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413702"},{"key":"e_1_2_11_10_1","doi-asserted-by":"crossref","unstructured":"XiaoH XuC CaoT ZhongL MunteanG. GTTC: a low\u2010expenditure IoT multi\u2010task coordinated distributed computing framework with fog computing.2019:1\u20106.","DOI":"10.1109\/GLOBECOM38437.2019.9013357"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.2993886"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2020.2985224"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988157"},{"key":"e_1_2_11_14_1","doi-asserted-by":"crossref","unstructured":"HauswaldJ KangY LaurenzanoMA et al. DjiNN and tonic: DNN as a service and its implications for future warehouse scale computers. 2015 ACM\/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA) Portland OR;2015:27\u201340.https:\/\/doi.org\/10.1145\/2749469.2749472.","DOI":"10.1145\/2749469.2749472"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2970550"},{"key":"e_1_2_11_16_1","article-title":"DeepHealth: a self\u2010attention based method for instant intelligent predictive maintenance in industrial Internet of things","author":"Zhang W","year":"2020","journal-title":"IEEE Trans Ind Inform"},{"key":"e_1_2_11_17_1","doi-asserted-by":"crossref","unstructured":"ZhangW YangD PengH et al. Deep reinforcement learning based resource management for DNN inference in IIoT;2020.","DOI":"10.1109\/GLOBECOM42002.2020.9322223"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","unstructured":"JeongH JeongI LeeH MoonS. Computation offloading for machine learning web apps in the edge server environment;2018:1492\u20101499.","DOI":"10.1109\/ICDCS.2018.00154"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2981411"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3004509"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2893250"},{"issue":"6","key":"e_1_2_11_23_1","first-page":"4950","article-title":"Toward collaborative inferencing of deep neural networks on Internet\u2010of\u2010Things devices","volume":"7","author":"Hadidi R","year":"2020","journal-title":"IEEE IoT J"},{"key":"e_1_2_11_24_1","doi-asserted-by":"crossref","unstructured":"QiB WuM ZhangL. A DNN\u2010based object detection system on mobile cloud computing;2017:1\u20106.","DOI":"10.1155\/2017\/2301970"},{"key":"e_1_2_11_25_1","doi-asserted-by":"crossref","unstructured":"ToshevA SzegedyC. DeepPose: human pose estimation via deep neural networks;2014:1653\u20101660.","DOI":"10.1109\/CVPR.2014.214"},{"key":"e_1_2_11_26_1","doi-asserted-by":"crossref","unstructured":"WeiSE RamakrishnaV KanadeT SheikhY.Convolutional pose machines. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;2016:4724\u20104732.","DOI":"10.1109\/CVPR.2016.511"},{"key":"e_1_2_11_27_1","doi-asserted-by":"crossref","unstructured":"ZhangF ZhuX YeM. Fast human pose estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;2019:3512\u20103521.","DOI":"10.1109\/CVPR.2019.00363"},{"issue":"99","key":"e_1_2_11_28_1","first-page":"1","article-title":"Smart collaborative balancing for dependable network components in cyber\u2010physical systems","author":"Song F","year":"2020","journal-title":"IEEE Trans Ind Inform"},{"issue":"7","key":"e_1_2_11_29_1","first-page":"6046","article-title":"Smart collaborative tracking for ubiquitous power IoT in edge\u2010cloud interplay domain","volume":"7","author":"Song F","year":"2020","journal-title":"IEEE IoT J"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2950109"},{"key":"e_1_2_11_31_1","first-page":"593","article-title":"Smart collaborative distribution for privacy enhancement in moving target defense","volume":"479","author":"Fei S","year":"2018","journal-title":"Inf Sci"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1800187"}],"container-title":["Transactions on Emerging Telecommunications Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ett.4263","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/ett.4263","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ett.4263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T13:49:16Z","timestamp":1693316956000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ett.4263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,6]]},"references-count":31,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["10.1002\/ett.4263"],"URL":"https:\/\/doi.org\/10.1002\/ett.4263","archive":["Portico"],"relation":{},"ISSN":["2161-3915","2161-3915"],"issn-type":[{"type":"print","value":"2161-3915"},{"type":"electronic","value":"2161-3915"}],"subject":[],"published":{"date-parts":[[2021,4,6]]},"assertion":[{"value":"2020-11-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-27","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e4263"}}