Arsitektur Hibrida Ekstraksi Fitur Lokal Edge Computing: Tinjauan Literatur Sistematis
DOI:
https://doi.org/10.37859/jf.v16i2.11806
Abstract
The proliferation of Internet of Things (IoT) devices and the demand for real-time processing have positioned edge computing as critical infrastructure for deploying deep learning models near the data source. Hardware constraints, including limited memory, narrow computational budgets, and strict power limits, challenge deployment of large-parameter neural architectures. This review examines hybrid architectures integrating convolutional neural networks (CNN) with attention mechanisms for local feature extraction on resource-constrained edge devices. Following the PRISMA 2020 protocol, a multi-stage search was conducted exclusively on Scopus, yielding 3,571 records, screened until 121 high-quality studies were included. The review addresses five research questions covering architectural trends, efficiency strategies, performance trade-offs, application domains, and federated learning for privacy-preserving deployment. Findings show that hybrid CNN-Attention architectures outperform pure CNN and Transformer baselines, with 3.2% average accuracy improvement while maintaining competitive inference latency on platforms such as NVIDIA Jetson and Raspberry Pi. Depthwise separable convolution, efficient channel attention, and token aggregation emerged as dominant compression strategies, with health imaging and fault diagnosis as leading domains. The review concludes that hybrid architectures represent the state of the art for edge-oriented local feature extraction, with future directions toward heterogeneous node generalization and multi-modal sensor fusion for distributed IoT networks.
Downloads
References
J. Lin, “CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer With Modality-Correlated Cross-Attention for Brain Tumor Segmentation,” IEEE Trans. Med. Imaging, vol. 42, no. 8, pp. 2451–2461, 2023, doi: 10.1109/TMI.2023.3250474.
D. Javeed, M. S. Saeed, M. Adil, P. Kumar, and A. Jolfaei, “A federated learning-based zero trust intrusion detection system for Internet of Things,” Ad Hoc Netw., vol. 162, p. 103540, 2024, doi: 10.1016/j.adhoc.2024.103540.
J. Yang, X. Chen, H. Zou, D. Wang, Q. Xu, and L. Xie, “EfficientFi: Toward Large-Scale Lightweight WiFi Sensing via CSI Compression,” IEEE Internet Things J., vol. 9, no. 15, pp. 13086–13095, 2022, doi: 10.1109/JIOT.2021.3139958.
F. Ma, B. Sun, and S. Li, “Facial Expression Recognition With Visual Transformers and Attentional Selective Fusion,” IEEE Trans. Affect. Comput., vol. 14, no. 2, pp. 1236–1248, 2023, doi: 10.1109/TAFFC.2021.3122146.
Z. Su, “Lightweight Pixel Difference Networks for Efficient Visual Representation Learning,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 12, pp. 14956–14974, 2023, doi: 10.1109/TPAMI.2023.3300513.
G. Xu, W. Jia, T. Wu, L. Chen, and G. Gao, “HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation,” IEEE Trans. Image Process., vol. 33, pp. 4202–4214, 2024, doi: 10.1109/TIP.2024.3425048.
L. Wang, “UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery,” ISPRS J. Photogramm. Remote Sens., vol. 190, pp. 196–214, 2022, doi: 10.1016/j.isprsjprs.2022.06.008.
M. Hassam, M. A. Khan, A. Armghan, S. A. Althubiti, and M. Alhaisoni, “A single stream modified MobileNet V2 and whale controlled entropy based optimization for skin lesion detection and classification,” IEEE Access, vol. 10, pp. 91496–91508, 2022, doi: 10.1109/ACCESS.2022.3201338.
H. Tan, X. Liu, B. Yin, and X. Li, “MHSA-Net: Multihead Self-Attention Network for Occluded Person Re-Identification,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 11, pp. 8210–8224, 2023, doi: 10.1109/TNNLS.2022.3144163.
T. Hussain, “EFFResNet-ViT: A fusion-based convolutional and vision transformer model for explainable medical image diagnosis,” IEEE Access, vol. 13, pp. 50312–50330, 2025, doi: 10.1109/ACCESS.2025.3554184.
Z. Meng, X. Xia, R. Xu, W. Liu, and J. Ma, “HYDRO-3D: Hybrid Object Detection and Tracking for Cooperative Perception Using 3D LiDAR,” IEEE Trans. Intell. Veh., vol. 8, no. 8, pp. 4069–4080, 2023, doi: 10.1109/TIV.2023.3282567.
X.-H. Nguyen, X.-D. Nguyen, H.-H. Huynh, and K.-H. Le, “Realguard: A Lightweight Network Intrusion Detection System for IoT Gateways,” Sensors, vol. 22, no. 2, p. 432, 2022, doi: 10.3390/s22020432.
X. Zhang, L. Han, W. Zhu, L. Sun, and D. Zhang, “An explainable 3D residual self-attention deep neural network for joint atrophy localization and Alzheimer’s disease diagnosis,” IEEE J. Biomed. Health Inform., vol. 26, no. 11, pp. 5394–5405, 2022, doi: 10.1109/JBHI.2021.3066832.
S. Ahmed, P. Abdalqadir, S. Abdullah, and Y. Haruna, “M2ANET: Mobile Malaria Attention Network for efficient classification of plasmodium parasites in blood cells,” Intel. Artif., vol. 28, pp. 186–199, 2025, doi: 10.4114/intartif.vol28iss76pp186-199.
Y. Kong, S. Lan, S. Lu, Z. Yang, and N. Huang, “HybirdRVIT-CNN: An improved vision transformer model for the recognition of onychomycosis in dermatoscopic images,” presented at the Proceedings of the International Conference on Big Data and Artificial Intelligence Applications (BDAIA 2025), 2026.
K. Zhou, C. Liu, Y. Zhang, R. Miao, S. Fu, and Y. Wang, “Enhanced Building Extraction via STMC-UNet: Integrating Super Token Transformer and Multi-scale Convolution,” Signal Image Video Process., vol. 19, no. 12, p. 1019, 2025, doi: 10.1007/s11760-025-04575-w.
X. Liu, W. Li, H. Li, Y. Zhu, and R. K. Agarwal, “Lightweight Gearbox Fault Diagnosis Under High Noise Based on Improved Multi-Scale Depthwise Separable Convolution and Efficient Channel Attention,” Sensors, vol. 26, no. 4, p. 1196, Feb. 2026, doi: 10.3390/s26041196.
S. Wan, Y. Wei, L. Kang, T. Shen, H. Wang, and Y.-H. Yang, “SciceVPR: Stable cross-image correlation enhanced model for visual place recognition,” Neurocomputing, vol. 669, p. 132539, Mar. 2026, doi: 10.1016/j.neucom.2025.132539.
S. Park, J. Kuai, H. Kim, H. Ko, C. Jung, and Y. Son, “A Lightweight Degradation-Aware Framework for Robust Object Detection in Adverse Weather,” Electronics, vol. 15, no. 1, p. 146, Dec. 2025, doi: 10.3390/electronics15010146.
J. Zhou, “HCLR-Net: Hybrid Contrastive Learning Regularization with Locally Randomized Perturbation for Underwater Image Enhancement,” Int. J. Comput. Vis., vol. 132, no. 10, pp. 4132–4156, 2024, doi: 10.1007/s11263-024-01987-y.
F. Li, X. Lv, M. Zhao, and W. Wu, “IFD-YOLO: A lightweight infrared sensor-based detector for small UAV targets,” Sensors, vol. 25, 2025, doi: 10.3390/s25154617.
U. Khatri and G.-R. Kwon, “Diagnosis of Alzheimer’s disease via optimized lightweight convolution-attention network,” Comput. Biol. Med., vol. 171, p. 108116, 2024, doi: 10.1016/j.compbiomed.2024.108116.
Y. Liu et al., “Fault Diagnosis Method for Excitation Dry-Type Transformer Based on Multi-Channel Vibration Signal and Visual Feature Fusion,” Sensors, vol. 25, no. 24, p. 7460, Dec. 2025, doi: 10.3390/s25247460.
S. Zhao, Y. Luo, T. Zhang, W. Guo, and Z. Zhang, “A domain specific knowledge extraction transformer method for multisource satellite remote sensing imagery road extraction,” ISPRS J. Photogramm. Remote Sens., vol. 198, pp. 341–352, 2023, doi: 10.1016/j.isprsjprs.2023.02.011.
A. Jiménez-Sánchez, “Memory-aware curriculum federated learning for breast cancer classification,” Comput. Methods Programs Biomed., vol. 229, p. 107318, 2023, doi: 10.1016/j.cmpb.2022.107318.
J. Wicaksana, Z. Yan, X. Yang, Y. Liu, L. Fan, and K.-T. Cheng, “Customized federated learning for multi-source decentralized medical image classification,” IEEE J. Biomed. Health Inform., vol. 27, no. 1, pp. 487–498, 2023, doi: 10.1109/JBHI.2022.3198440.
R. Kumar, “Blockchain and homomorphic encryption based privacy-preserving model aggregation for medical images,” Comput. Med. Imaging Graph., vol. 102, p. 102139, 2022, doi: 10.1016/j.compmedimag.2022.102139.
J. Guo, I. W.-H. Ho, Y. Hou, and Z. Li, “FedPos: A federated transfer learning framework for CSI-based Wi-Fi indoor positioning,” IEEE Syst. J., vol. 17, no. 2, pp. 2490–2501, 2023, doi: 10.1109/JSYST.2022.3230425.
H. Wang, R. Gu, J. Wang, X. Zhang, and H. Wei, “GFL-SAR: Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement,” Comput. Mater. Contin., vol. 86, no. 1, pp. 1–20, 2026, doi: 10.32604/cmc.2025.069251.
Md. W. Rahman et al., “Privacy-Preserving Federated IoT Architecture for Early Stroke Risk Prediction,” Electronics, vol. 15, no. 1, p. 32, Dec. 2025, doi: 10.3390/electronics15010032.
C. Cahyaningtyas, Mira, C. Gudiato, and M. Sari, “Deteksi Ekspresi Wajah Manusia Menggunakan Metode Convolutional Neural Network,” Jurnal FASILKOM, vol. 15, no. 1, pp. 138–145, 2025, doi: 10.37859/jf.v15i1.9119.
R. Aldin, “Implementasi Convolutional Neural Network pada Deteksi Penyakit Retina Menggunakan Citra Fundus Mata,” Jurnal FASILKOM, vol. 15, no. 3, 2025, doi: 10.37859/jf.v15i3.9857.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Wildan Zhilal Manafi, Nabhani Fatin, Ade Bastian
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright Notice
An author who publishes in the Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) agrees to the following terms:
- Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal
- Author is able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book) with the acknowledgement of its initial publication in this journal.
- Author is permitted and encouraged to post his/her work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of the published work (See The Effect of Open Access).
Read more about the Creative Commons Attribution-ShareAlike 4.0 Licence here: https://creativecommons.org/licenses/by-sa/4.0/.
