Advances, Systems and Applications
Refs | Area | Aims | Methods | Dataset | Advantages |
---|---|---|---|---|---|
Lu et al. [94] | IOV | Protect passenger privacy | GCN | 20newsgroups | better than VFL |
Ye et al. [85] | IOV | Reduce the Impact of Heterogeneity Problems in Vehicle Clients on Federated Learning Performance | selective polymerization | MNIST & BelgiumTSC | better than approaches based on FedAvg. |
Bao et al. [95] | IOV | Implement client selection and networking solutions in a car networking environment | Fuzzy logic algorithm | n/a | Communication-efficient |
Boualouache and Engel [86] | IOV | Detect passive mobile attackers in 5G vehicle edge computin | MLP | n/a | Fast Detection & High Accuracy |
Xu et al. [96] | IOV | Accurately schedule and dynamically reserve the appropriate amount of multimedia service resources on edge servers. | ST ResNet | n/a | Secure and efficient |
Fantacci and Picano [97] | Demand prediction | Protect sensitive user data | FedAvg | MovieLens 1M & MovieLens 100K | better than the approach based on chaos theory and deep learning. |
Taïk and Cherkaoui [98] | Household load forecasting | Protect user privacy | FedAvg | n/a | significant gain in the network load |
Rahbari et al. [99] | UAV | Improve resource utilization in real-time applications. | Aggregate by scoring weight | n/a | better fairness & energy efficient |
Pham et al. [100] | UAV | Improve the transmit power efficiency of UAVs | Decomposition | n/a | Dramatically reduce drone launch power |
Chen et al. [101] | Augmented Reality | Improve computational efficiency & Reduce latency | CNN | CIFAR-10 | Fewer training iterations |
Hsu et al. [102] | Information Security | Android malware detection | SVM | from NICT | Outperforms centralized training systems. |
Wang et al. [103] | Industry | Industrial Equipment Troubleshooting | Asynchronous update | n/a | Communication-efficient & Fast Convergence |
Zhang et al. [104] | IOMT | Adapt FL to train AHD models | FedSens | real-world AHD applications | strong for biased class distributions |
Qayyum et al. [89] | Healthcare | Automated diagnosis of COVID-19 | CFL | COVID-19 CT segmentation | Outperforms traditional FL models |
Yuan et al. [105] | Intelligent Transport | Traffic flow forecast | FedSTN | n/a | accurate and fast prediction |
Vyas et al. [106] | Intelligent Transport | Calculate driving stress and the relationship between driving stress and driving behavior | Long Short-Term Memory Fully Convolutional Network | UAH | High pressure prediction accuracy |
Sada et al. [107] | Video Analysis | Distributed video analysis framework | distributed object detection | n/a | Real-time Distributed Object Detection |
Chen et al. [87] | Cyber Security | Intrusion detection of wireless networks | FedAGRU | KDD CUP 99 & CICIDS2017 | Communication-efficient & strong robustness against poisoning attacks |
Li et al. [93] | Cyber Security | Detect network attacks | FLEAM | n/a | Approximate accuracy to centralized training. & Greatly increase detection rate. |
Huong et al. [92] | Cyber Security | Quickly and accurately identify cyber attackers | Centralized and distributed methods | BoT-IoT | Accuracy and complexity outperform CNN, SVM and other algorithms. |
Hu et al. [108] | Smart City | Urban environment sensing | FRL | n/a | Energy-efficient |