No abstract

Federated learning (FL) can empower Internet-of-Vehicles (IoV) networks by leveraging smart vehicles (SVs) to participate in the learning process with minimum data exchanges and privacy disclosure. The collected data and learned knowledge can help the vehicular service provider (VSP) improve the global model accuracy, e.g., for road safety as well as better profits for both VSP and participating SVs. Nonetheless, there exist major challenges when implementing the FL in IoV networks, such as dynamic activities and diverse quality-of-information (QoI) from a large number of SVs, VSP's limited payment budget, and profit competition among SVs. In this paper, we propose a novel dynamic FL-based economic framework for an IoV network to address these challenges. Specifically, the VSP first implements an SV selection method to determine a set of the best SVs for the FL process according to the significance of their current locations and information history at each learning round. Then, each selected SV can collect on-road information and offer a payment contract to the VSP based on its collected QoI. For that, we develop a multi-principal one-agent contract-based policy to maximize the profits of the VSP and learning SVs under the VSP's limited payment budget and asymmetric information between the VSP and SVs. Through experimental results using real-world on-road datasets, we show that our framework can converge 57% faster (even with only 10% of active SVs in the network) and obtain much higher social welfare of the network (up to 27.2 times) compared with those of other baseline FL methods.

The objective of this study was to investigate the responses of peanut genotypes to midseason drought, regarding in particular nutrient uptakes and their correlations with biomass production and pod yield. The experiment was conducted during the dry seasons of 2011/12 and 2012/13. Five peanut genotypes with different levels of drought tolerance and 2 water regimes (well-watered and midseason drought) were laid out in a split-plot design with 4 replications. Midseason drought was imitated by stopping irrigation at 30 days after planting (DAP) and then rewatering at 60 DAP. The data were recorded for contents of N, P, K, Ca, and Mg in plant tissues, biomass production, yield components, and pod yield at harvest. The results showed that midseason drought significantly reduced the uptake of all nutrient elements. Peanut genotypes with higher levels of drought tolerance took up more nutrients than those with lower levels. The uptake of all nutrient elements contributed to biomass production, pod yield, and the number of pods per plant. ICGV 98305 was the best genotype with the highest uptakes of all observed nutrient elements.

No abstract

No abstract