Tracking mobile targets is a basic task for many applications, e.g., wildlife protection, area surveillance, battlefield reconnaissance, disaster rescue, etc. In these cases, multiple edge devices are usually deployed to collect images or videos from the target area. Two mainstream tracking methodologies have been proposed to recognize and track targets from such data sources cooperatively. The centralized strategies collect data from the edge devices and thereafter run mining and learning algorithms upon such data. On the contrary, the distributed strategies implement such algorithms in a distributed manner. However, these methods incur either high transmission costs or slow convergence speeds. To this end, this paper presents a novel cooperative tracking framework (i.e., FedTrack) based on adaptive federated learning. A dual reputation mechanism has been formulated, and subsequently, an adaptive node selection algorithm has been suggested to ascertain the nodes suitable for involvement in the training process. Furthermore, a strategy for selecting the aggregation node based on capability has been developed to enhance the efficiency of aggregation. As far as we know, FedTrack is the first federated learning framework for collaborative tracking. Experimental results demonstrate that FedTrack achieves comparable or even better accuracy than state-of-the-art methods, yet needs much fewer data transmission costs and much less time consumption.

Blockchain-based federated learning (BCFL) has been regarded as an emerging data sharing paradigm in edge networks of internet-of-things (IoT) because of its advantages, such as decentralization, collaborative model training, and privacy protection. However, there have been few studies focusing on strategic analysis in the BCFL system, which is important for establishing a robust and sustainable BCFL system in an untrustworthy and profit-driven environment. In this paper, we first propose a self-organizing data sharing system supported by BCFL to deeply analyze the data sharing logic. Then, a mathematical model based on evolutionary game theory is established to analyze the interaction between model owners and data providers, aiming at exploring the stability of user strategies under different considerations. According to the strategic analysis, we designed and further discussed a dynamic system control mechanism based on smart contracts to adaptively maintain a robust and sustainable BCFL system. We conducted numerical analysis and experiments to verify our work.

The recent convergence of blockchain-based federated learning (BCFL) offers enhanced data privacy, traceability, and ownership protection for decentralized data sharing. However, current research lacks consensus on accurate and fair data valuation methods for decentralized environments—a critical yet unresolved challenge. Existing Shapley value (SV)-based data valuation methods, while promising, rely on centralized frameworks ill-suited for decentralized environments and incur high computational costs. To address this, we propose a scalable dual-chain architecture: the main chain handles primary BCFL data-sharing operations, while a dedicated side-chain offloads data valuation tasks. For the side chain, we introduce the proof-of-lightweight-Shapley (PoLS) protocol, enabling decentralized SV computation with theoretical convergence guarantees. PoLS leverages a proof-of-work (PoW)-inspired mechanism to facilitate parallel and lightweight computation of SVs using Monte Carlo sampling. Furthermore, we develop an SV-based data aggregation protocol to validate PoLS effectiveness and enhance resilience against low-quality data attacks. Extensive experiments confirm that PoLS significantly reduces computational overhead while maintaining an average deviation as low as 2.3% from the true SV. Moreover, in adversarial scenarios, the PoLS-driven aggregation strategy improves model accuracy by 25.7% over baselines, thereby strengthening the robustness and fairness of the decentralized valuable data sharing.