Deep Learning With Edge Computing: A Review
The DOI matches its Crossref record; 130 of the 141 references it cites were found in a registry or an index.
Abstract
Deep learning is currently widely used in a variety of applications, including computer vision and natural language processing. End devices, such as smartphones and Internet-of-Things sensors, are generating data that need to be analyzed in real time using deep learning or used to train deep learning models. However, deep learning inference and training require substantial computation resources to run quickly. Edge computing, where a fine mesh of compute nodes are placed close to end devices, is a viable way to meet the high computation and low-latency requirements of deep learning on edge devices and also provides additional benefits in terms of privacy, bandwidth efficiency, and scalability. This paper aims to provide a comprehensive review of the current state of the art at the intersection of deep learning and edge computing. Specifically, it will provide an overview of applications where deep learning is used at the network edge, discuss various approaches for quickly executing deep learning inference across a combination of end devices, edge servers, and the cloud, and describe the methods for training deep learning models across multiple edge devices. It will also discuss open challenges in terms of systems performance, network technologies and management, benchmarks, and privacy. The reader will take away the following concepts from this paper: understanding scenarios where deep learning at the network edge can be useful, understanding common techniques for speeding up deep learning inference and performing distributed training on edge devices, and understanding recent trends and opportunities.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“As mentioned in Section 2.1, the progress of DL is very fast but when it comes to application in Edge or IoT devices then a huge gap is noticeable [67].”
From A survey on deep transfer learning to edge computing for mitigating the COVID-19 pandemic (2020) · cites this paper as [67]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
(2016) · Cited by 31,590
Research works printed but not linked: 30
- Jeans, 2019, Related’s Hudson Yards: Smart City or Surveillance City?
- AT&T Multi-Access Edge Computing
- Blog, Edge Computing at Chick-Fil-A
- Goodfellow, 2016, Deep Learning, 1
- 10.1145/3299710.3211336 · DOI · Paper page
- Tensorflow
- Tensorflowlite
- Caffe2
- Caffe
- Pytorch
- Cuda
- Cudnn
- AWS Deeplens
- Deep Learning for Siri’s Voice: On-Device Deep Mixture Density Networks for Hybrid Unit Selection Synthesis
- Google Duplex: An AI System for Accomplishing Real-World Tasks Over the Phone
- Pagespeed Insights: Improve Server Response Time
- 2017, Hey Siri: An On-Device DNN-Powered Voice Trigger for Apple’s Personal Assistant
- Google’s Pixel Buds are no Match for Professional Interpreters
- Jindal, 2018, Enabling Full Body AR With Mask R-CNN2GO
- 10.1145/3081333.3081360 · DOI · Paper page
- Edge TPU.
- VPU.
- NVIDIA EGX Edge Computing Platform
- Qualcomm Neural Processing SDK for AI
- 10.1109/MNET.2018.1700202 · DOI · Paper page
- Arcore Overview
- Teerapittayanon, 2017, BranchyNet: Fast inference via early exiting from deep neural networks, CoRR, abs/1709.01686, 1 · arXiv
- 10.1145/3195970.3196023 · doi:10.1145/3195970.3196023 · Paper page
- Hsieh, Gaia: Geo-distributed machine learning approaching LAN speeds, 629
- 10.1109/NCA.2017.8171350 · DOI · Paper page
Cited by
Items 601–700 of 1,000
Deep learning in multiagent systems
Esterle, L. (2022) · Elsevier eBooks · doi:10.1016/b978-0-32-385787-1.00022-1 · Cited by 15
MDSC: modelling distributed stream processing across the edge-to-cloud continuum
Balouek‐Thomert, D., Silva, P., Fauvel, K., Costan, A., Antoniu, G., & Parashar, M. (2021) · IEEE/ACM International Conference on Utility and Cloud Computing Companion (UCC Companion) · doi:10.1145/3492323.3495590 · Cited by 11
“Several studies [14, 21] identified the main vectors driving a shift towards using resources at the Edge of the network, near the data sources, building what is called the Edge intelligence [32]: ML training and ML inference at the Edge.”
Power-of-2-arms for bandit learning with switching costs
Shi, M., Lin, X., & Jiao, L. (2022) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3492866.3549720 · Cited by 9
“Moreover, we present a motivating example based on edge computing with artificial intelligence (Edge AI), which has received extensive attention recently [6].”
InfluentialRTCoInfer: Real-Time Collaborative CNN Inference for Stream Analytics on Ubiquitous Images
Zhang, Z., Yang, S., Zhao, C., Ren, X., Yu, H., Han, Q., & Guo, S. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3242730 · Cited by 10
“To improve the efficiency of CNN inference and support real-time applications, Collaborative Inference (CI) between the local device and remote server is being rapidly promoted [8], [9].”
Optimizing Task-Specific Timeliness With Edge-Assisted Scheduling for Status Update
Sun, J., Wang, L., Nan, Z., Sun, Y., Zhou, S., & Niu, Z. (2023) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2023.3329017 · Cited by 11
“For example, in Augmented Reality (AR) applications, a headset needs to continuously capture the position of certain objects and render virtual elements [6].”
BackgroundDube, S., Wan, W. Y., & Nugroho, H. (2021) · IEEE Access · doi:10.1109/access.2021.3059251 · Cited by 11
“Therefore, it would be a much more feasible solution to deploy certain parts of a deep learning model to the IoT edge device in an effort to assist the cloud in the entire continuous learning process instead of relying completely on the cloud [19].”
BackgroundA Survey on Applications of Deep Learning in Cloud Radio Access Network
Rodoshi, R. T., & Choi, W. (2021) · IEEE Access · doi:10.1109/access.2021.3074180 · Cited by 13
“The authors in [12] discussed various methods for fast application of DL inference across a variety of edge devices, edge servers, and the cloud.”
BackgroundMethodQi, P. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/2890473 · Cited by 9
“MEC is an efficient method to overcome the challenge by offloading some latency-sensitive tasks or computationintensive to nearby edge servers through wireless communication [10, 11].”
MethodEff-AQI: An Efficient CNN-Based Model for Air Pollution Estimation: A Study Case in India
Utomo, S., Rouniyar, A., Jiang, G. H., Chang, C. H., Tang, K. C., Hsu, H.-C., & Hsiung, P. (2023) · International Conference on Information Technology for Social Good (GoodIT) · doi:10.1145/3582515.3609531 · Cited by 10
Over-the-Air Federated Averaging With Limited Power and Privacy Budgets
Yan, N., Wang, K., Pan, C., Chai, K. K., Shu, F., & Wang, J. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3338738 · Cited by 13
“The conventional strategy for training these models is to aggregate all these raw data to a central server with high computing capability, where the training is performed [2].”
BackgroundMatassoni, M., Fong, S., & Brutti, A. (2024) · Applied Sciences · doi:10.3390/app14093876 · Cited by 9
A Framework for Selecting and Assessing Wearable Sensors Deployed in Safety Critical Scenarios
Houghton, R., Martinetti, A., & Majumdar, A. (2024) · Sensors · doi:10.3390/s24144589 · Cited by 9
Spatial Computing Opportunities in Biomedical Decision Support: The Atlas-EHR Vision
Farhadloo, M., Sharma, A., Shekhar, S., & Markovic, S. N. (2024) · ACM Transactions on Spatial Algorithms and Systems · doi:10.1145/3679201 · Cited by 20
“However, these studies are either limited to specific types of EHR data and lack a comprehensive perspective regarding the EHR data across the human body as a system of systems [ 1 , 72 ] through the lens of spatial computing research.”
Mhapsekar, R. U., Abraham, L., Davy, S., & Dey, I. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3475634 · Cited by 10
Shen, B., Ma, Q., Yang, G., Wang, R., & Ji, W. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3486351 · Cited by 8
One-core neuron deep learning for time series prediction
Peng, H., Chen, P., Yang, N., Aihara, K., Liu, R., & Chen, L. (2024) · National Science Review · doi:10.1093/nsr/nwae441 · Cited by 13
Rapid and Automatic UAV Detection of River Embankment Piping
Duan, Q., Chen, B., & Luo, L. (2025) · Water Resources Research · doi:10.1029/2024wr038931 · Cited by 9
“…because UAV‐based applications commonly involve a large amount of data transmission for processing on cloud services or locally, edge computing (J. Chen & Ran, 2019; Iyer & Roychowdhury, 2023) enables data processing and analysis close to the source, which is highly conducive to rapid UAV‐based…”
Ning, B., Zeng, L., Fan, K., & Chen, F. (2025) · Ultrasonics · doi:10.1016/j.ultras.2025.107598 · Cited by 9
Intelligent Monitoring of Tunnel Fire Smoke Based on Improved YOLOX and Edge Computing
Li, C., Zhu, B., Chen, G., Li, Q., & Xu, Z. (2025) · Applied Sciences · doi:10.3390/app15042127 · Cited by 10
IoT-Edge Splitting With Pruned Early-Exit CNNs for Adaptive Inference
Korol, G., & Beck, A. C. S. (2025) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2025.3543445 · Cited by 11
“Compared to cloud-only processing, edge alleviates the network traffic, offers reduced latency, and improves security with fewer data exposure [16], [17].”
A novel computer vision-based approach for autonomous building facade material stock estimation
Rajaratnam, D., Stewart, R. A., Liu, T., & Vieira, A. S. (2025) · Resources Conservation and Recycling · doi:10.1016/j.resconrec.2025.108311 · Cited by 10
“Additionally, their reduced computational demands create potential opportunities for integrating results with edge device applications (Chen and Ran, 2019).”
Large Language Models on Small Resource-Constrained Systems: Performance Analysis and Trade-Offs
Seymour, L., Kütükçü, B., & Baidya, S. (2025) · IEEE SoutheastCon · doi:10.1109/southeastcon56624.2025.10971638 · Cited by 11
“Fully on-device generation/computation is one of multiple use cases for deep learning models on embedded devices [17].”
Deep learning-based intelligent visual inspection for defect detection in smoke sensor manufacturing
Wan, A., Wu, Z., & AL-Bukhaiti, K. (2025) · Next research. · doi:10.1016/j.nexres.2025.100424 · Cited by 11
Best Practices for the Deployment of Edge Inference: The Conclusions to Start Designing
Flamis, G., Kalapothas, S., & Kitsos, P. (2021) · Electronics · doi:10.3390/electronics10161912 · Cited by 9
“Quantization of the parameters takes an existing neural network and compresses its parameters by changing from floating-point numbers to low-bit width numbers, thus avoiding costly floating-point multiplications [112,113].”
Early Termination Based Training Acceleration for an Energy-Efficient SNN Processor Design
Choi, S., Lew, D., & Park, J. (2022) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2022.3181808 · Cited by 8
Ma, H., Zhang, J., Gu, Z., Kilper, D. C., & Ji, Y. (2023) · Journal of Optical Communications and Networking · doi:10.1364/jocn.498951 · Cited by 8
A cloud‐edge service offloading method for the metaverse in smart manufacturing
Xiang, H., Zhang, X., & Bilal, M. (2023) · Software Practice and Experience · doi:10.1002/spe.3301 · Cited by 11
“15,16 For practical scheduling, each ECD’s computing capacity is assumed to be lighter than the cloud in the implementation of edge computing.”
Reconfigurable Precision SRAM-based Analog In-memory-compute Macro Design
Bazzi, J., Jamil, R., ElHajj, D., Kanj, R. N., Fouda, M. E., & Eltawil, A. M. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558662 · Cited by 8
“Over the past decade, neural networks (NNs) have emerged as a powerful tool used in various fields, including healthcare, security, finance, and autonomous vehicles [1]–[5].”
BackgroundChen, H., Wang, X., Xiao, Y., Wu, B. X., Wang, Z., Liu, Y., Wang, P., Chen, C., & Wu, X. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1457623 · Cited by 12
“However, due to the computational power limitations of edge devices, large datasets are challenging for deep learning models to fit and can reduce the speed of forward computations (Chen and Ran, 2019).”
BackgroundWu, L., Xiao, G., Huang, D., Zhang, X., Ye, D., & Weng, H. (2025) · Agronomy · doi:10.3390/agronomy15010242 · Cited by 11
Sohn, V., Kim, S., & Lee, H.-W. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3539356 · Cited by 10
“Recently, with the increasing demand for deep learning-based services on mobile devices, the problem of partitioning and offloading DNN computations for inference has been actively studied as well [9], [10].”
Edge Computing in Healthcare Systems
Mulimani, M. S., & Rachh, R. R. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-60265-9_5 · Cited by 9
Self-Adaptive Approximate Mobile Deep Learning
Knez, T., Machidon, O. M., & Pejović, V. (2021) · Electronics · doi:10.3390/electronics10232958 · Cited by 9
DNN inference offloading for object detection in 5G multi-access edge computing
Kim, G.-Y., Kim, R., Kim, S., Nam, K.-D., Rha, S.-U., & Yoon, J. (2021) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc52510.2021.9620821 · Cited by 8
Nakahara, M., Hisano, D., Nishimura, M., Ushiku, Y., Maruta, K., & Nakayama, Y. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625464 · Cited by 10
“In particular, the EC system that provides artificial A part of this work was supported by JSPS KAKENHI Grant Numbers JP20H04178 and GMO Foundation, Japan. intelligence applications such as image recognition, objective detection, and other solutions that rely on deep neural network (DNN) [3], [4].”
MethodReal-Time, CNN-Based Assistive Device for Visually Impaired People
Jouini, K., Maaloul, M. H., & Korbaa, O. (2021) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei53629.2021.9624387 · Cited by 8
A Thermal Infrared Pedestrian-Detection Method for Edge Computing Devices
You, S., Ji, Y., Liu, S., Mei, C., Yao, X., & Feng, Y. (2022) · Sensors · doi:10.3390/s22176710 · Cited by 8
“The edge computing devices for these series are only Internet-ofThings terminal devices, which have low computing power and power consumption [19].”
BackgroundZhao, J., Yang, M., Zhang, R., Song, W., Zheng, J., Feng, J., & Matwin, S. (2022) · Electronics · doi:10.3390/electronics11234007 · Cited by 13
Blockchain-Based Continuous Knowledge Transfer in Decentralized Edge Computing Architecture
Jin, W., Xu, Y., Dai, Y., & Xu, Y. (2023) · Electronics · doi:10.3390/electronics12051154 · Cited by 13
Honarparvar, S., Saeedi, S., Liang, S. H. L., & Squires, J. (2021) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi10020081 · Cited by 9
“An alternative solution would be to use an architecture based on edge computing technology to provide privacy [13].”
BackgroundSyReNN: A Tool for Analyzing Deep Neural Networks
Sotoudeh, M., & Thakur, A. (2021) · Lecture notes in computer science · doi:10.26226/morressier.604907f41a80aac83ca25cde · Cited by 10
Comparative Evaluation of Machine Learning Inference Machines on Edge-class Devices
Amanatidis, P., Iosifidis, G., & Karampatzakis, D. (2021) · Panhellenic Conference on Informatics · doi:10.1145/3503823.3503843 · Cited by 8
“In combination with the hardware, the ML frameworks offer rich software libraries and APIs for developers to create robust applications for demanding environments [3].”
BackgroundBottino, L., Settino, M., & Cannataro, M. (2024) · Springer eBooks · doi:10.1007/978-3-031-70310-2_2 · Cited by 9
Performance Prediction for Convolutional Neural Networks in Edge DevicesPreprint
Bouzidi, H., Ouarnoughi, H., Niar, S., & Cadi, A. A. E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.11297 · Cited by 13
“Consequently, finding the CNN which gives the best trade-off between accuracy and execution time is a tedious task [1].”
BackgroundAI at the Physical Layer for Wireless Network Security and Privacy
Abdalla*, A. S., Tang, B., & Marojevic, V. (2024) · Wiley eBooks · doi:10.1002/9781394227952.ch10 · Cited by 12
Event-based Classification with Recurrent Spiking Neural Networks on Low-end Micro-Controller Units
Boretti, C., Prono, L., Frenkel, C., Indiveri, G., Pareschi, F., Mangia, M., Rovatti, R., & Setti, G. (2023) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas46773.2023.10181998 · Cited by 9
“Indeed, the use of DNNs on mobile Internet of Things (IoT) devices is of great interest, with numerous potential applications [1], [2].”
BackgroundGugssa, M. W., Li, L., Pu, L., Gürbüz, A. C., Luo, Y., & Wang, J. (2024) · Engineering Construction & Architectural Management · doi:10.1108/ecam-07-2023-0763 · Cited by 13
Design and Optimization of Hierarchical Gradient Coding for Distributed Learning at Edge Devices
Tang, W., Li, J., Chen, L., & Chen, X. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3418901 · Cited by 10
“Due to its profound benefits, such hierarchical workers-edge-master architecture has been introduced into many distributed learning systems [4], [5], [9], [10], [11], [12].”
Lightweight Detection Counting Method for Pill Boxes Based on Improved YOLOv8n
Sun, W., Niu, X., Wu, Z., & Guo, Z. (2024) · Electronics · doi:10.3390/electronics13244953 · Cited by 7
Potato late blight leaf detection in complex environments
Li, J., Wu, J., Liu, R., Shu, G., Liu, X., Zhu, K., Wang, C., & Zhu, T. (2024) · Scientific Reports · doi:10.1038/s41598-024-82272-3 · Cited by 7
“However, the limited storage and performance of these edge devices make traditional detection models unsuitable 31 .”
Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters
Pei, Q., Yuan, Y., Hu, H., Wang, L., Zhang, D., Yan, B., Chen, Y., & Liu, F. (2025) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2025.3542563 · Cited by 7
“DNN inference has become a core component in various intelligent edge applications [32], [33].”
Optimisation Strategies for Next-Generation AI, ML, and IoT Applications
Hassan, M. A. M., Fahim, M. F. H., Usman, M. M., Sardar, T. H., Mondal, M. A., & Khan, M. A. (2025) · Springer tracts on transportation and traffic · doi:10.1007/978-3-031-87627-1_10 · Cited by 8
Feng, Q., Lu, Z., Zhang, L., Li, C., Huang, F., Weng, J., & Yu, P. S. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3576692 · Cited by 9
“For instance, when the image data volume becomes substantial, the data owner may deploy a distributed computing cluster to optimize model training efficiency [30], [31], [32].”
A scientometric review of digital twin in 3G to 6G networks: industry applications and trends
Bhatia, M., & Malik, V. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02679-1 · Cited by 9
A Survey of AI Inference Technologies for On-Device Systems
Wang, W., Li, K., Ji, B., Liu, X., Yu, J., & Wu, Q. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3613691 · Cited by 16
Paul, S., Venu, E., Sarkar, M., Das, S., Roy, A., & Sinha, P. (2025) · Plant Methods · doi:10.1186/s13007-025-01453-x · Cited by 11
“MobileNetV3 is an enhanced lightweight CNN and optimized architecture balances computational efficiency with classification accuracy, making it suitable for field deployment [33, 37, 38].”
YOLO11-SPE: a lightweight object detection model for corn seedling counting
Wu, Y., Luo, Y., Chen, H., Chen, F., Ye, H., Chen, X., & Li, X. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01825-5 · Cited by 7
“Existing models typically increase computational overhead and model size while improving accuracy, which presents challenges for real-time processing and edge device [16] deployment.”
Zhang, S., Wang, Z., Wang, L., Ran, W., Tianxu, Y., Zhang, X., Wei, B., Deng, Q., & Shen, G. (2025) · Advanced Materials · doi:10.1002/adma.202520626 · Cited by 7
“However, DPC in-sensor device is limited by its operational process: simultaneously sensing and processing can only occur in the front light-exposing layer, thus it is incapable to sustain DNN for tasks of high complexity [40].”
Real-time cognitive workload assessment using non-intrusive methods: a systematic review
Basnet, N., & Zahabi, M. (2025) · Ergonomics · doi:10.1080/00140139.2025.2606779 · Cited by 11
Evaluating policy-driven adaptation on the Edge-to-Cloud Continuum
Balouek‐Thomert, D., Rodero, I., & Parashar, M. (2021) · IEEE/ACM HPC for Urgent Decision Making (UrgentHPC) · doi:10.1109/urgenthpc54802.2021.00007 · Cited by 11
Pedestrian and Vehicle Detection Based on Pruning YOLOv4 with Cloud-Edge Collaboration
Wang, H., Mo, R., Chen, Y., Lin, W., Xu, M., & Liu, B. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.026910 · Cited by 7
User authentication and access control to blockchain-based forensic log data
Islam, M. E., Islam, M. R., Chetty, M., Lim, S., & Chadhar, M. (2023) · EURASIP Journal on Information Security · doi:10.1186/s13635-023-00142-3 · Cited by 10
“We implement that immutable data storage in permissioned blockchain within an edge network as edge computing also increases the scalability by executing computations close to the end devices [8].”
MethodPutrada, A. G., Abdurohman, M., Perdana, D., & Nuha, H. H. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-47715-7_41 · Cited by 7
On-board drone classification with Deep Learning and System-on-Chip implementation
Cecio, G. D., Manco, A., & Gigante, G. E. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2716/1/012059 · Cited by 15
“Edge AI is the intersection between edge computing and Artificial Intelligence, it consists of deploy AI algorithm computation directly on the edge device of a network, instead of relying on a cloud-based processing [9]-[11].”
BackgroundMethodArtificial Intelligence of Things: Architectures, Applications, and Challenges
Ahvar, E., Ahvar, S., & Lee, G. M. (2023) · Springer handbooks · doi:10.1007/978-3-031-39650-2_19 · Cited by 11
A Multiply-And-Max/Min Neuron Paradigm for Aggressively Prunable Deep Neural Networks
Prono, L., Bich, P., Boretti, C., Mangia, M., Pareschi, F., Rovatti, R., & Setti, G. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3527644 · Cited by 10
“The use of DNNs at the edge on mobile Internet of Things (IoT) devices is of great interest due to the high potential it unlocks [3], [4], [5] and for its wide range of applications from augmented reality [6], natural language processing [7], computer vision [8], and compressed sensing for…”
Compressed Private Aggregation for Scalable and Robust Federated Learning Over Massive Networks
Lang, N., Shlezinger, N., D’Oliveira, R. G. L., & Rouayheb, S. E. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3564390 · Cited by 12
“FL [2], [3], [4], [5] is an emerging paradigm for training a model on multiple edge devices, exploiting their computational capabilities [6].”
Özkurt, C. (2025) · Türk doğa ve fen dergisi :/Türk doğa ve fen dergisi · doi:10.46810/tdfd.1529139 · Cited by 12
DNN Placement and Inference in Edge Computing
Bensalem, M., Dizdarević, J., & Jukan, A. (2020) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro48935.2020.9245108 · Cited by 7
“The rapid development of DL techniques, as a result of both the hardware and software advancements, as well as the increasing demand for data processing at the network edge has led to the new research direction, which sees these two trends combined [1].”
BackgroundEnergy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence
Daghero, F., Burrello, A., Pagliari, D. J., Benini, L., Macii, E., & Poncino, M. (2020) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs49266.2020.9294863 · Cited by 16
“Hardware accelerators achieve impressive efficiency but are only affordable for high-budget and highvolume products [1].”
BackgroundMemcached: An Experimental Study of DDoS Attacks for the Wellbeing of IoT Applications
Mishra, N. C., Pandya, S., Patel, C. I., Cholli, N. G., Modi, K. J., Shah, P., Chopade, M., Patel, S., & Kotecha, K. V. (2021) · Sensors · doi:10.3390/s21238071 · Cited by 7
“The latency involved in a smart grid ranges from milliseconds to subseconds [42].”
BackgroundBattiloro, C., Merluzzi, M., Lorenzo, P. D., & Barbarossa, S. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746891 · Cited by 7
de Souza, P. H. C., & Mendes, L. L. (2022) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-022-02152-0 · Cited by 9
“A detailed evaluation of system end-to-end latency [17, 18], for example, is out of scope in this work.”
BackgroundEdge Computing-Assisted DNN Image Recognition System With Progressive Image Retransmission
Nakahara, M., Nishimura, M., Ushiku, Y., Nishio, T., Maruta, K., Nakayama, Y., & Hisano, D. (2022) · IEEE Access · doi:10.1109/access.2022.3202172 · Cited by 8
A Data-Driven Model for Automated Chinese Word Segmentation and POS Tagging
Xu, Q., & Wang, Z. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/7622392 · Cited by 10
Energy Efficient LSTM Accelerators for Embedded FPGAs Through Parameterised Architecture Design
Qian, C., Ling, T., & Schiele, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42785-5_1 · Cited by 7
Song, L., Wang, H., & Yang, B. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-023-05663-9 · Cited by 7
“With the development of edge computing technology [3–5], fault diagnosis could occur at the front end.”
Artificial Intelligence Advancement for 6G Communication: A Visionary Approach
Miya, J., Raj, S., Ansari, M. A., Kumar, S. M., & Kumar, R. (2023) · Springer eBooks · doi:10.1007/978-3-031-30101-8_15 · Cited by 10
Lightweight Fault Prediction Method for Edge Networks
Yang, Y., Mei, J., Zhang, Z., Long, Y., Liu, A., Gao, Z., & Rui, L. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3333293 · Cited by 7
“Although a deep learning method called a GRU simplifies the design of memory units, LSTM seems to be more effective than GRU, particularly in dealing with the nonlinearity of larger data sets [18].”
BackgroundMethodInformed Prefetching in I/O Bounded Distributed Deep Learning
Ruan, X., & Chen, H. (2021) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw52791.2021.00127 · Cited by 7
“Today a large number of deep learning services are offered on mobile devices and cloud servers via edge computing [3].”
BackgroundInnovative Vineyards Environmental Monitoring System Using Deep Edge AI
Coppola, M., Noaille, L., Pierlot, C., de Oliveira, R. O., Vaillant‐Gaveau, N., Rondeau, M., Mohimont, L., Steffenel, L. A., Sindaco, S., & Salmon, T. (2022) · River Publishers eBooks · doi:10.1201/9781003337232-23 · Cited by 7
Developing Practical Multi-view Learning for Clinical Analytics in P4 Medicine
Nan, Y., Li, W., Lu, F., Luo, C., Li, J., & Zomaya, A. Y. (2021) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2021.3054761 · Cited by 7
Wang, Y., Wei, Z., Huang, Z., Yang, J., & Zhao, J. (2024) · Cluster Computing · doi:10.1007/s10586-024-04732-9 · Cited by 6
Intrusion Detection at the Edge Computing: A Deep Learning Approach Using the UNSW-NB15 Dataset
Kumar, V., Kumar, V., Bhadauria, A. P. S., Dixit, J., & Kumar, A. P. S. (2025) · IEEE International Conference on Communication Systems and Network Technologies (CSNT) · doi:10.1109/csnt64827.2025.10968274 · Cited by 6
“For the performance of the models evaluated by these important parameters because effective and efficient IDS holds the minimum FPR and Maximum DR for classification purpose to detect the normal and abnormal network traffic efficiently [18][19].”
Adaptive joint configuration optimization for collaborative inference in edge-cloud systems
Yang, Z., Ji, W., & Wang, Z. (2024) · Science China Information Sciences · doi:10.1007/s11432-023-3957-4 · Cited by 6
Chong, Z., Ge, X., Liu, B., & Yuan, X. (2025) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2025.107402 · Cited by 9
Deploying Optimized Deep Vision Models for Eyeglasses Detection on Low-Power Platforms
Giedra, H., Sledević, T., & Matuzevičius, D. (2025) · Electronics · doi:10.3390/electronics14142796 · Cited by 7
Soil moisture monitoring technologies in smart agriculture: A comprehensive review
Sreeram, R., Krishna, S. A., Kumar, A. S., Remya, S., & Cho, Y. (2025) · Farming System · doi:10.1016/j.farsys.2025.100189 · Cited by 17
Post-training quantization for efficient FPGA-based neural network acceleration
Salah, O. B. H., Messaoud, S., Hajjaji, M. A., Atri, M., & Liouane, N. (2025) · Integration · doi:10.1016/j.vlsi.2025.102508 · Cited by 10
Robyns, S., Helsen, S., Weckx, S., Bhoi, S. K., Baghdadi, M. E., Hegazy, O., & Smet, J. D. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2022.12.267 · Cited by 8
Yang, H., Huang, Y., Shi, J., & Yang, Y. (2023) · Journal of Grid Computing · doi:10.1007/s10723-023-09658-x · Cited by 8
“The latest technologies at the intersection of deep learning and edge computing was presented in [6].”
BackgroundA Mobile Robot Based on Edge AI
Santos, R. C. C. D. M., Silva, M. C., Santos, R. L., Klippel, E., & Oliveira, R. (2023) · Anais do Seminário Integrado de Software e Hardware (SEMISH) · doi:10.5753/semish.2023.230539 · Cited by 6
“Despite this challenge, there is a growing trend of combining these two concepts, particularly in the domain of mobile edge computing [Chen and Ran 2019].”
BackgroundEndoDepthL: Lightweight Endoscopic Monocular Depth Estimation with CNN-Transformer
Li, Y. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10386008 · Cited by 9
“Since algorithms must operate in real-time on edge devices like endoscopes, we cannot directly apply algorithms developed for specialized graphical computing devices to such equipment [18], [19].”
MethodADC/DAC-Free Analog Acceleration of Deep Neural Networks With Frequency Transformation
Darabi, N., Hashem, M. B., Pan, H., Çetin, A. E., Gomes, W., & Trivedi, A. R. (2024) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2024.3375111 · Cited by 6
“I N RECENT years, deep learning has gained significant traction in critical domains such as healthcare, finance, security, and autonomous vehicles [1], [2], [3], [4], [5].”
Kaur, M., Cheng, H., & Kourtessis, P. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3598355 · Cited by 8
“Many of these advanced applications require substantial computation, which strains resource-constrained mobile devices [10]–[12].”
Bi-direction Context Propagation Network for Real-time Semantic Segmentation.
Hao, S., Zhou, Y., Guo, Y., & Hong, R. (2020) · Cited by 7
Custom-IP for Gradient Descent Optimization based on Hardware/Software Co-design Paradigm
Shabarinath, B. B., & Muralidhar, P. (2020) · International Symposium on VLSI Design and Test (VDAT) · doi:10.1109/vdat50263.2020.9190560 · Cited by 6
An Edge-Cloud Framework Equipped with Deep Learning Model for Recyclable Garbage Detection
Luo, Q., Yang, G., & Zhao, X. (2020) · International Conference on Advanced Cloud and Big Data · doi:10.1109/cbd51900.2020.00052 · Cited by 7
“In edge computing, computations are done locally on end user devices to reduce latency and protect privacy [10].”
BackgroundJi, X., Chen, K., Chen, M., Li, Y., & Qian, X. (2022) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2022.102634 · Cited by 6
Deep Odometry Systems on Edge with EKF-LoRa Backend for Real-Time Indoor Positioning
Dai, Z., Saputra, M. R. U., Lu, C. X., Vu, T. H., Wijayasingha, L. N., Rahman, M. A., Stankovic, J. A., Markham, A., & Trigoni, N. (2022) · doi:10.1109/cps-er56134.2022.00007 · Cited by 6
“Common deployment methods are yet limited to a one-off network minimization upon a specific piece of hardware, such as knowledge distillation [4].”
Background
Metadata
- Authors
- Chen, J., & Ran, X.
- Affiliations
- University of California, Riverside (US)
- ORCID
- Chen, Jiasi
- Venue
- Proceedings of the IEEE
- Published
- 2019-08
- Volume
- 107
- Issue
- 8
- Pages
- 1655-1674
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W2960833983
- Cited by
- 1,540
- References
- 141
- Citations by year
- 2026: 205 · 2025: 250 · 2024: 270 · 2023: 245 · 2022: 232 · 2021: 218 · 2020: 114 · 2019: 6
- FWCI
- 77.78
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- Funders
- National Science Foundation (CNS-1817216)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Keywords
- edge computing, deep learning, edge inference, distributed deep learning training, edge servers, cloud-edge collaboration, Internet of Things, low latency, privacy, spectral efficiency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.