A wearable flexible tri-annular square ring monopole antenna with artificial magnetic conductor (AMC) is proposed. The antenna operates at the ISM band (2.28-2.51 GHz, 5.2-6 GHz) and at WiMAX band (3.5-4GHz) for wireless body area network (WBAN) applications. The number of antenna operating bands is determined by the number of square rings. A tri-band AMC array is integrated to reduce the specific absorption rate (SAR) and the antenna profile. The overall size of antenna with AMC array is 90 Â 90 Â 6 mm 3 . The peak gain of the antenna is 4.8, 5.1, and 6.2 dBi at three frequency bands, respectively. The proposed antenna and AMC were printed on a flexible polyimide film. The antenna has good conformity, easy processing, lightweight and low profile of 0.048 λ 0 at 2.4 GHz. The antenna was fabricated and measured where a very good agreement between simulated and measured results for S 11 and radiation pattern. The measured antenna radiation efficiency is more than 70% in the operating frequency band.

No abstract

Point-of-Interest (POI) recommendation is significant in location-based social networks to help users discover new locations of interest. Previous studies on such recommendation mainly adopted a centralized learning framework where check-in data were uploaded, trained and predicted centrally in the cloud. However, such a framework suffers from privacy risks caused by check-in data exposure and fails to meet real-time recommendation needs when the data volume is huge and communication is blocked in crowded places. In this paper, we propose PREFER, an edge-accelerated federated learning framework for POI recommendation. It decouples the recommendation into two parts. Firstly, to protect privacy, users train local recommendation models and share multi-dimensional user-independent parameters instead of check-in data. Secondly, to improve recommendation efficiency, we aggregate these distributed parameters on edge servers in proximity to users (such as base stations) instead of remote cloud servers. We implement the PREFER prototype and evaluate its performance using two real-world datasets and two POI recommendation models. Extensive experiments demonstrate that PREFER strengthens privacy protection and improves efficiency with little sacrifice to recommendation quality compared to centralized learning. It achieves the best quality and efficiency and is more compatible with increasingly sophisticated POI recommendation models compared to other state-of-the-art privacy-preserving baselines.

No abstract

No abstract