Future sixth-generation (6G) mobile communication networks are expected to include new features such as the network data analysis function (NWDAF), which will allow network operators to integrate machine learning (ML)-based data analysis techniques into their networks. This will allow NWDAF to identify, safeguard against, and handle various types of anomalous behaviors on user devices. To this end, this study applies fair federated learning (FL) to the 3GPP standard NWDAF architecture and embeds the designed multi-task ML model to detect traffic anomalies in different types of user devices. However, there is a problem of different task demands when the same ML model is used for optimization between different tasks. Therefore, a global alternating gradient projection (AGP) technique is presented in this study. It can be applied to many tasks and utilized to solve minimization problems. The two gradient projection phases comprise each iteration of the AGP. These steps update various tasks at regular intervals, thereby providing a regularized version of the gradient to the original multi-task objective function, which results in optimal task performance. The simulation results demonstrate that the proposed multi-task ML model can simultaneously detect traffic anomalies of different types of user devices in NWDAF and outperforms state-of-the-art models in detecting multi-task anomalies in NWDAF. The experimental evaluation also implied that the designed FL applies superior anomaly detection performance in NWDAF scenarios and has lower communication overhead than that of the traditional NWDAF without affecting the ML performance.
1 January 2020 in IEEE Transactions on Industrial Electronics
The neighbor discovery process (NDP) plays a key role in BLE-enabled applications. However, when a massive number of BLE devices are involved in the NDP, signal collisions become severer, which degrade the NDP performance seriously. To solve the problem, BLE 5.0 specifies some extended features such as advanced NDP (A-NDP). The previous works on the performance models for the NDP have focused on the basic NDP (B-NDP). Though some works considered the performance evaluations on A-NDP, they have done on simulations or testbed-based experiments. Likewise, so far, the performance analysis for A-NDP has been insufficient. In this paper, we propose an analytical model to evaluate A-NDP performances such as the signal collision probability, the discovery delay, the energy consumption and so on. With the proposed analysis model, the performances of A-NDP are analyzed from the viewpoint of various operational environments for BLE-enabled IoT services, and compared to those of B-NDP with extended features of Bluetooth 5.0. Besides, it showed that A-NDP is not always better than B-NDP, and we discuss the operational conditions where A-NDP or B-NDP operate effectively, respectively.
23 January 2025 in IEEE Transactions on Intelligent Transportation Systems
The rapid development of intelligent transportation and autonomous driving technologies, driven by the Internet of Vehicles (IoV), faces significant challenges owing to data and system heterogeneity. These challenges stem from the multidomain nature of the IoV and threats such as data leaks and model-finding attacks, which complicate data processing and model training. To address these issues, in this study, we proposed federated multi-domain learning for IoV (FMD-IoV). FMD-IoV addresses data heterogeneity by employing clustered techniques to group similar viewpoints and multidomain machine learning to map diverse data types into a unified feature space. To address the system heterogeneity caused by diverse vehicle types, the framework introduces a similarity-based aggregation method and model weight de-regularization to enhance robustness and generalizability. Experimental results demonstrated that FMD-IoV reduced the mean square error (MSE) by 0.05 on the Synthia dataset and 0.13 on the CityScape dataset compared with the state-of-the-art methods. Moreover, it maintained or improved the MSE as the number of nodes increased, demonstrating its adaptability to complex scenarios and large-scale data. These results highlight the flexibility, resilience, and efficacy of FMD-IoV in multi-view data fusion within large-scale IoV environments.
18 February 2022 in IEEE Internet of Things Journal
Bluetooth low-energy (BLE) technology is one of the most promising communication technologies applicable to a variety of Internet of Things (IoT) services. The neighbor discovery process (NDP) plays a key role in BLE-enabled IoT services. The basic NDP (B-NDP) specified in BLE specification 4.0 has a limitation in supporting large numbers of BLE devices, owing to its use of three channels. To overcome the limitation of B-NDP, advanced NDP (A-NDP) has been recently introduced in BLE specification 5.0. However, most existing studies have focused on B-NDP, with very few studies having been conducted on A-NDP. In this article, we propose a model for analyzing the effective transmission rate for a BLE advertiser with an A-NDP operation. Using the proposed model, we also propose a performance model to maximize the transmission rate by optimally setting the BLE parameters. The proposed models are validated by comparing with extensive simulation results. It also demonstrates that the maximum transmission rate by the proposed models can be achieved with low energy consumption.
28 August 2025 in IEEE Transactions on Consumer Electronics
The rapid proliferation of consumer electronics and Internet of Things (IoT) devices demands intelligent, scalable, and privacy-preserving learning paradigms capable of handling diverse tasks and domains. In this work, we propose FM Learning, a novel Federated Multi-Task Multi-Domain learning framework based on lightweight large models. FM is designed to simultaneously address three key challenges in real-world distributed environments: (1) statistical heterogeneity across client data distributions, (2) functional variability across tasks, and (3) resource constraints on edge devices. Unlike conventional federated learning approaches that assume task homogeneity, our method clusters clients into task-specific groups and enables collaborative model training across both task and domain boundaries. We introduce a dual management strategy using task-related dual variables to balance shared and personalized representations, while leveraging a distributed optimization scheme for scalable model updates. Extensive experiments on benchmark datasets including Office-Caltech-10, DomainNet, MNIST, and SVHN show that FM consistently outperforms state-of-the-art methods such as FedAvg and FedDGA, achieving up to 3.6% higher top-1 accuracy on DomainNet and 4.8% F1-score improvement on KDD Cup’99, highlighting its robustness in heterogeneous and resource-limited settings.
Federated learning as a distributed category yields sub-optimal performance for the presence of Non-iid in multi-domain data. To this end, we proposes a novel clustered federated framework for unsupervised multi-domain network anomaly detection, which implements dynamic clustered federated based on the data distribution of different domain so that each edge user learns the domain-optimized inference model. Compared to baseline, the proposed method enables users to obtain domain-optimal performance.