A Literature Review on Model Conversion, Inference, and Learning Strategies in EdgeML with TinyML Deployment
Source abstract
Abstract
Edge Machine Learning (EdgeML) and Tiny Machine Learning (TinyML) are fast-growing fields that bring machine learning to resource-constrained devices, allowing real-time data processing and decision-making at the network’s ... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Innovation in Digital Healthcare Systems · Technology and Data Analysis · Cloud Computing and Resource Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (100+)
Show source-provided references
1. Deep learning modelling techniques: current progress, applications, advantages, and challenges10.1007/s10462-023-10466-8 ↗
2. Internet of intelligent things: a convergence of embedded systems, edge computing and machine learning10.1016/j.iot.2024.101153 ↗
3. A literature review of IoT and CPS—what they are, and what they are not10.1016/j.jss.2023.111631 ↗
4. Cloud computing security: a survey of service-based models10.1016/j.cose.2021.102580 ↗
5. Edge AI: a survey10.1016/j.iotcps.2023.02.004 ↗
6. Combining federated learning and edge computing toward ubiquitous intelligence in 6G network: challenges, recent advances, and future directions10.1109/COMST.2023.3316615 ↗
7. Communication-efficient distributed learning: an overview10.1109/JSAC.2023.3242710 ↗
8. Edge computing on IoT for machine signal processing and fault diagnosis: a review10.1109/JIOT.2023.3239944 ↗
9. Tiny machine learning for resource-constrained microcontrollers10.1155/2022/7437023 ↗
10. A review on the emerging technology of TinyML10.1145/3661820 ↗
11. Revisiting edge AI: opportunities and challenges10.1109/MIC.2024.3383758 ↗
12. Edge computing with artificial intelligence: a machine learning perspective10.1145/3555802 ↗
13. A survey on edge intelligence and lightweight machine learning support for future applications and services10.1145/3581759 ↗
14. Model compression of deep neural network architectures for visual pattern recognition: current status and future directions10.1016/j.compeleceng.2024.109180 ↗
15. Combining machine learning and edge computing: opportunities, challenges, platforms, frameworks, and use cases10.3390/electronics13030640 ↗
16. A machine learning-oriented survey on tiny machine learning10.1109/ACCESS.2024.3365349 ↗
17. Machine learning security and privacy: a review of threats and countermeasures
18. Knowledge distillation: a survey10.1007/s11263-021-01453-z ↗
19. Deepthings: distributed adaptive deep learning inference on resource-constrained iot edge clusters10.1109/TCAD.2018.2858384 ↗
20. Konečný J, McMahan HB, Ramage D, Richtárik P. Federated optimization: distributed machine learning for on-device intelligence. arXiv:161002527. 2016.
21. Optimizing deep neural networks on intelligent edge accelerators via flexible-rate filter pruning10.1016/j.sysarc.2022.102431 ↗
22. Asymptotic soft filter pruning for deep convolutional neural networks10.1109/TCYB.2019.2933477 ↗
23. Pruning filters with L1-norm and capped L1-norm for CNN compression10.1007/s10489-020-01894-y ↗
24. EasiEdge: a novel global deep neural networks pruning method for efficient edge computing10.1109/JIOT.2020.3034925 ↗
25. Adaptive CNN filter pruning using global importance metric10.1016/j.cviu.2022.103511 ↗
26. UFKT: unimportant filters knowledge transfer for CNN pruning10.1016/j.neucom.2022.09.150 ↗
27. Enhancing CNN efficiency through mutual information-based filter pruning10.1016/j.dsp.2024.104547 ↗
28. FPWT: filter pruning via wavelet transform for CNNs10.1016/j.neunet.2024.106577 ↗
29. Multi-objective evolutionary architectural pruning of deep convolutional neural networks with weights inheritance10.1016/j.ins.2024.121265 ↗
30. Towards extreme face and periocular recognition model compression with mixed-precision quantization10.1016/j.engappai.2024.109114 ↗
31. Minimal loss DNN model compression with vectorized weight quantization10.1109/TC.2020.2995593 ↗
32. Deep network quantization via error compensation10.1109/TNNLS.2021.3064293 ↗
33. Smart-DNN+: a memory-efficient neural networks compression framework for the model inference10.1145/3617688 ↗
34. MBQuant: a novel multi-branch topology method for arbitrary bit-width network quantization10.1016/j.patcog.2024.111061 ↗
35. MedQ: lossless ultra-low-bit neural network quantization for medical image segmentation10.1016/j.media.2021.102200 ↗
36. Hardware deployable edge-AI solution for prescreening of oral tongue lesions using TinyML on embedded devices10.1109/LES.2022.3160281 ↗
37. A practical wearable fall detection system based on tiny convolutional neural networks10.1016/j.bspc.2023.105325 ↗
38. An ultra-low power tinyml system for real-time visual processing at edge
39. Automated quantization and retraining for neural network models without labeled data10.1109/ACCESS.2022.3190627 ↗
40. EfficientQ: an efficient and accurate post-training neural network quantization method for medical image segmentation10.1016/j.media.2024.103277 ↗
41. MPQ-YOLO: ultra low mixed-precision quantization of YOLO for edge devices deployment10.1016/j.neucom.2023.127210 ↗
42. GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework10.1016/j.neunet.2018.01.010 ↗
43. SYMOG: learning symmetric mixture of Gaussian modes for improved fixed-point quantization10.1016/j.neucom.2019.11.114 ↗
44. Quantization through search: a novel scheme to quantize convolutional neural networks in finite weight space
45. Hessian-based mixed-precision quantization with transition aware training for neural networks10.1016/j.neunet.2024.106910 ↗
46. HamQ: hamming weight-based energy aware quantization for analog compute-in-memory accelerator in intelligent sensors
47. Learning to quantize deep networks by optimizing quantization intervals with task loss
48. Deep convolutional neural network compression via coupled tensor decomposition10.1109/JSTSP.2020.3038227 ↗
49. Sparse low rank factorization for deep neural network compression10.1016/j.neucom.2020.02.035 ↗
50. Compression of deep neural networks based on quantized tensor decomposition to implement on reconfigurable hardware platforms10.1016/j.neunet.2022.02.024 ↗
51. Joint matrix decomposition for deep convolutional neural networks compression10.1016/j.neucom.2022.10.021 ↗
52. Filter-based deep-compression with global average pooling for convolutional networks10.1016/j.sysarc.2019.02.008 ↗
53. A knowledge distillation based deep learning framework for cropped images detection in spatial domain10.1016/j.image.2024.117117 ↗
54. A light-weight skeleton human action recognition model with knowledge distillation for edge intelligent surveillance applications10.1016/j.asoc.2023.111166 ↗
55. A novel lightweight deep learning framework with knowledge distillation for efficient diabetic foot ulcer detection10.1016/j.asoc.2024.112296 ↗
56. A novel model compression method based on joint distillation for deepfake video detection10.1016/j.jksuci.2023.101792 ↗
57. Difficulty level-based knowledge distillation10.1016/j.neucom.2024.128375 ↗
58. Hybrid knowledge distillation from intermediate layers for efficient single image super-resolution10.1016/j.neucom.2023.126592 ↗
59. Leveraging different learning styles for improved knowledge distillation in biomedical imaging10.1016/j.compbiomed.2023.107764 ↗
60. Multidimensional knowledge distillation for multimodal scene classification of remote sensing images10.1016/j.dsp.2024.104876 ↗
61. A multi-resolution fusion approach for human activity recognition from video data in tiny edge devices10.1016/j.inffus.2023.101953 ↗
62. DeepWear: adaptive local offloading for on-wearable deep learning10.1109/TMC.2019.2893250 ↗
63. DNNOff: offloading DNN-based intelligent IoT applications in mobile edge computing10.1109/TII.2021.3075464 ↗
64. An efficient DNN splitting scheme for edge-AI enabled smart manufacturing
65. DDPQN: an efficient DNN offloading strategy in local-edge-cloud collaborative environments10.1109/TSC.2021.3116597 ↗
66. Self-aware collaborative edge inference with embedded devices for IIoT10.1016/j.future.2024.107535 ↗
67. Edge-device collaborative computing for multi-view classification10.1016/j.comnet.2024.110823 ↗
68. Model and system robustness in distributed CNN inference at the edge10.1016/j.vlsi.2024.102299 ↗
69. Distributed inference in resource-constrained iot for real-time video surveillance10.1109/JSYST.2022.3198711 ↗
70. PCNN CEC: efficient and privacy-preserving convolutional neural network inference based on cloud-edge-client collaboration10.1109/TNSE.2022.3177755 ↗
71. DOCTOR: a multi-disease detection continual learning framework based on wearable medical sensors10.1145/3679050 ↗
72. Latent replay for real-time continual learning
73. A tinyml platform for on-device continual learning with quantized latent replays10.1109/JETCAS.2021.3121554 ↗
74. On-device training of fully quantized deep neural networks on Cortex-M microcontrollers
75. LEAF: an adaptation framework against noisy data on edge through ultra low-cost training
76. Fast deep autoencoder for federated learning10.1016/j.patcog.2023.109805 ↗
77. Enabling efficient and low-effort decentralized federated learning with the EdgeFL framework10.1016/j.infsof.2024.107600 ↗
78. Efficient knowledge management for heterogeneous federated continual learning on resource-constrained edge devices10.1016/j.future.2024.02.018 ↗
79. Importance-aware data selection and resource allocation for hierarchical federated edge learning10.1016/j.future.2023.12.014 ↗
80. FedDA: resource-adaptive federated learning with dual-alignment aggregation optimization for heterogeneous edge devices10.1016/j.future.2024.107551 ↗
81. Federated learning framework based on trimmed mean aggregation rules10.1016/j.eswa.2024.126354 ↗
82. Xu J, Wang S, Wang L, Yao AC-C. FedCM: federated learning with client-level momentum. arXiv:210610874. 2021.
83. Probabilistic predictions with federated learning10.3390/e23010041 ↗
84. Dynamic aggregation for heterogeneous quantization in federated learning10.1109/TWC.2021.3076613 ↗
85. Federated learning: a cutting-edge survey of the latest advancements and applications10.1016/j.comcom.2024.107964 ↗
86. The path to smart farming: innovations and opportunities in precision agriculture10.3390/agriculture13081593 ↗
87. A tinyml-based system for smart agriculture
88. TinyML for smart agriculture: comparative analysis of TinyML platforms and practical deployment for maize leaf disease identification
89. Deploying an energy efficient, secure & high-speed sidechain-based TinyML model for soil quality monitoring and management in agriculture10.1016/j.eswa.2023.122735 ↗
90. TinyML implementation on microcontrollers: the case of maize leaf disease identification
91. Lite-Agro: exploring light-duty computing platforms for IoAT-Edge AI in plant disease identification.In
92. Detecting face masks through embedded machine learning algorithms: a transfer learning approach for affordable microcontrollers
93. BandX: an intelligent IoT-band for human activity recognition based on TinyML
94. Optimized tiny machine learning and explainable AI for trustable and energy-efficient fog-enabled healthcare decision support system10.1007/s44196-024-00631-4 ↗
95. MHCNLS-HAR: multi-headed CNN-LSTM based human activity recognition leveraging a novel wearable edge device for elderly health care10.1109/JSEN.2024.3450499 ↗
96. The case for TinyML in healthcare: CNNs for real-time on-edge blood pressure estimation
97. Online processing of vehicular data on the edge through an unsupervised TinyML regression technique10.1145/3591356 ↗
98. TEDA-RLS: a TinyML incremental learning approach for outlier detection and correction10.1109/JSEN.2024.3458917 ↗
99. TinyML-based intrusion detection system for in-vehicle network using convolutional neural network on embedded devices
100. IoT-Fog-based framework to prevent vehicle-road accidents caused by self-visual distracted drivers10.1007/s11042-024-19050-w ↗