Topological Dependencies in Deep Learning for Mobile Edge: Distributed and Collaborative High-Speed Inference
Edge computing is now widely deployed across the globe. Although the Internet serves as the foundation for edge computing, the actual usefulness of this type of computing is seen when it is combined with the process of obtaining data from sensors and deriving relevant information from that data. It...
Uloženo v:
| Vydáno v: | 2023 Second International Conference on Electronics and Renewable Systems (ICEARS) s. 1165 - 1171 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
02.03.2023
|
| Témata: | |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Edge computing is now widely deployed across the globe. Although the Internet serves as the foundation for edge computing, the actual usefulness of this type of computing is seen when it is combined with the process of obtaining data from sensors and deriving relevant information from that data. It is predicted that in the not-too-distant era, most edge devices will be equipped with intelligent systems powered by deep learning. Unfortunately, in order to train, methods based on deep learning require a significant quantity of data of a high standard, and these methods are quite costly in terms of the amount of processing, memory, and power that they use. Distributed deep neural networks, or DDNNs, are something suggested by using distributed computing hierarchies. The cloud, fog, and devices make up these tiers. Although a DDNN can facilitate the interpretation of a DNN in the cloud, it also allows for interpretation to be carried out quickly and precisely on the edges and on end devices by making use of shallow parts of the neural network. With the help of a scalable cloud-based infrastructure, a DDNN can expand both in terms of volume of its neural network and the number of users it serves around the world. For DNN applications, the distributed nature of DDNNs results in improvements to sensor fusion, fault tolerance in the system, and data privacy. In order to implement DDNN, first the portions of a DNN are mapped onto a dispersed computing structure. By learning both components together, the devices' need become limited for both connectivity and energy while the model provided the value of the selected features in the cloud. The final product includes provision for instinctive sensor fusion as well as fault tolerance that has been built directly into the system. This study demonstrates as a proof of concept that a DDNN may make use of the geographical variety of sensors to improve the accuracy of object detection and lower the cost of communication. The suggested method achieves both rapid convergence and good accuracy thanks to the use of stochastic gradient (SGD), which capitalizes on edge collaborative learning. |
|---|---|
| AbstractList | Edge computing is now widely deployed across the globe. Although the Internet serves as the foundation for edge computing, the actual usefulness of this type of computing is seen when it is combined with the process of obtaining data from sensors and deriving relevant information from that data. It is predicted that in the not-too-distant era, most edge devices will be equipped with intelligent systems powered by deep learning. Unfortunately, in order to train, methods based on deep learning require a significant quantity of data of a high standard, and these methods are quite costly in terms of the amount of processing, memory, and power that they use. Distributed deep neural networks, or DDNNs, are something suggested by using distributed computing hierarchies. The cloud, fog, and devices make up these tiers. Although a DDNN can facilitate the interpretation of a DNN in the cloud, it also allows for interpretation to be carried out quickly and precisely on the edges and on end devices by making use of shallow parts of the neural network. With the help of a scalable cloud-based infrastructure, a DDNN can expand both in terms of volume of its neural network and the number of users it serves around the world. For DNN applications, the distributed nature of DDNNs results in improvements to sensor fusion, fault tolerance in the system, and data privacy. In order to implement DDNN, first the portions of a DNN are mapped onto a dispersed computing structure. By learning both components together, the devices' need become limited for both connectivity and energy while the model provided the value of the selected features in the cloud. The final product includes provision for instinctive sensor fusion as well as fault tolerance that has been built directly into the system. This study demonstrates as a proof of concept that a DDNN may make use of the geographical variety of sensors to improve the accuracy of object detection and lower the cost of communication. The suggested method achieves both rapid convergence and good accuracy thanks to the use of stochastic gradient (SGD), which capitalizes on edge collaborative learning. |
| Author | Ala Walid, Md. Abul S, Balu Abd Algani, Yousef Methkal Sasi Kumar, A. Kumar, A Suresh Velayutham, Priya |
| Author_xml | – sequence: 1 givenname: Yousef Methkal surname: Abd Algani fullname: Abd Algani, Yousef Methkal email: yosefabdalgani@gmail.com organization: The Arab Academic College for Education in Israel-Haifa,Department of Mathematics,Israel – sequence: 2 givenname: A Suresh surname: Kumar fullname: Kumar, A Suresh email: suresh.cse@rathinam.in organization: Rathinam Technical Campus,Department of Computer Science and Engineering,Coimbatore,Tamil Nadu,India – sequence: 3 givenname: Md. Abul surname: Ala Walid fullname: Ala Walid, Md. Abul email: abulalawalid@gmail.com organization: Khulna University of Engineering & Technology (KUET),Khulna,Bangladesh,9203 – sequence: 4 givenname: Balu surname: S fullname: S, Balu email: sbalu26@gmail.com organization: Vivekanandha College of Engineering for Women,Department of Computer Science and Engineering,Namakkal,Tamil Nadu,India – sequence: 5 givenname: Priya surname: Velayutham fullname: Velayutham, Priya email: priyasaravanaraju@gmail.com organization: Paavai Engineering College,Department of Computer Science and Engineering,Namakkal,Tamil Nadu,India – sequence: 6 givenname: A. surname: Sasi Kumar fullname: Sasi Kumar, A. email: askmca@yahoo.com organization: Inurture Education Solutions Pvt Ltd,Bangalore |
| BookMark | eNo1kM1KAzEURiPoQmvfwEV8gKk3PzOZuCvTagsVwdZ1ySQ3Y2CaDJlR8O0tqKuPw4Gz-G7IZUwRCblnsGAM9MO2WS_f9mUlNF9w4GLBAGqpRXlB5lrpWpQgZFVJuCanQxpSn7pgTU9XOGB0GG3AkYZ4ZhzoDk2OIXbUp0xfUht6pGvX4SNdhXHKof2c0FETHW1S35s2ZTOFL6Sb0H0U-wHPchs95nMWb8mVN_2I87-dkfen9aHZFLvX522z3BWBMT0VlVCWK6OUQdB1DcoaaSVqp0tneGkltNpZ9L5uSy1BKeEBDLdce1E75sSM3P12AyIehxxOJn8f_18QPyLCWLw |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/ICEARS56392.2023.10084935 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9798350346640 |
| EndPage | 1171 |
| ExternalDocumentID | 10084935 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IL CBEJK RIE RIL |
| ID | FETCH-LOGICAL-i119t-637c27a77ae098807ca4c4e9d95da25c40b9dceff8b5940773f00a2c29f38d1d3 |
| IEDL.DBID | RIE |
| IngestDate | Wed Aug 27 07:42:26 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i119t-637c27a77ae098807ca4c4e9d95da25c40b9dceff8b5940773f00a2c29f38d1d3 |
| PageCount | 7 |
| ParticipantIDs | ieee_primary_10084935 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-March-2 |
| PublicationDateYYYYMMDD | 2023-03-02 |
| PublicationDate_xml | – month: 03 year: 2023 text: 2023-March-2 day: 02 |
| PublicationDecade | 2020 |
| PublicationTitle | 2023 Second International Conference on Electronics and Renewable Systems (ICEARS) |
| PublicationTitleAbbrev | ICEARS |
| PublicationYear | 2023 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 1.8602927 |
| Snippet | Edge computing is now widely deployed across the globe. Although the Internet serves as the foundation for edge computing, the actual usefulness of this type... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1165 |
| SubjectTerms | Cloud Cloud computing Computational modeling Deep learning Deep neural network Edge computing Fault tolerance Fault tolerant systems high-speed inference Image edge detection machine intelligence Training |
| Title | Topological Dependencies in Deep Learning for Mobile Edge: Distributed and Collaborative High-Speed Inference |
| URI | https://ieeexplore.ieee.org/document/10084935 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF5sEfGkYkXrgxW8pk02m-yuN-kDC1qKrdBb2cds6cG09PX73d2mFg8evCUhMDCzw8wk830fQk-ui5BZSt2Qw20eUZB5pHLXyElITGqYtVoHyvw31u_z8VgMSrB6wMIAQFg-g4a_DP_yzVxv_KeypieioSLNKqjCWL4Da52gx5I3s9lrdV4-hpmruR5hRdLG_v1fyimhcHTP_mnyHNUOEDw8-CkuF-gIikv0NdpJGnjH4nYpX-uSc4VnhbuHBS7pUqfY9aL4fa5czuOOmcIzbnuGXC9uBQbLwuDW4QBsAft1j2i4cNZwb2-_hj67nVHrNSr1EqJZkoh1lKdMEyYZkxALl5dMS6opCCMyI0mmaayE0WAtV5lwgxxLbRxLoomwKTcuNleoWswLuEZYxgI04YonIKnKteCGKoDYaDdPg-Q3qOZ9NVnsKDEmezfV_3h-i059RMLyFrlD1fVyA_foWG_Xs9XyIQTyG2-_ojA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8JAEJ0oGvWkRozfronXQrvddne9GYRABEIEE25kuzslHCyEr9_vbikSDx68tU2aSWZ2MjPtvPcAnm0XoaKQ2SFHpLHHUMVeEttGTmFgQsPTVOucMr_Nu10xHMpeAVbPsTCImC-fYcVd5v_yzVSv3KeyqiOiYTKM9uEgYoz6G7jWETwVzJnVVq3--tGPbNV1GCsaVrZv_NJOyUtH4_SfRs-gvAPhkd5PeTmHPcwu4GuwETVwriVvhYCtTc8FmWT2HmekIEwdE9uNks40sVlP6maML-TNceQ6eSs0RGWG1HZHYI3ELXx4_Zm1Rlpb-2X4bNQHtaZXKCZ4kyCQSy8OuaZcca7QlzYzuVZMM5RGRkbRSDM_kUZjmookknaU42Hq-4pqKtNQGBudSyhl0wyvgChfoqYiEQEqlsRaCsMSRN9oO1GjEtdQdr4azTakGKOtm27-eP4Ix81Bpz1qt7rvt3DiopOvctE7KC3nK7yHQ71eThbzhzyo3wuRpXc |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2023+Second+International+Conference+on+Electronics+and+Renewable+Systems+%28ICEARS%29&rft.atitle=Topological+Dependencies+in+Deep+Learning+for+Mobile+Edge%3A+Distributed+and+Collaborative+High-Speed+Inference&rft.au=Abd+Algani%2C+Yousef+Methkal&rft.au=Kumar%2C+A+Suresh&rft.au=Ala+Walid%2C+Md.+Abul&rft.au=S%2C+Balu&rft.date=2023-03-02&rft.pub=IEEE&rft.spage=1165&rft.epage=1171&rft_id=info:doi/10.1109%2FICEARS56392.2023.10084935&rft.externalDocID=10084935 |