English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Fine-grained location prediction on smart phones can be used to improveapp/system performance. Application scenarios include video quality adaptationas a function of the 5G network quality at predicted user locations, andaugmented reality apps that speed up content rendering based on predicted userlocations. Such use cases require prediction error in the same range as the GPSerror, and no existing works on location prediction can achieve this level ofaccuracy. We present a system for fine-grained location prediction (FGLP) ofmobile users, based on GPS traces collected on the phones. FGLP has twocomponents: a federated learning framework and a prediction model. Theframework runs on the phones of the users and also on a server that coordinateslearning from all users in the system. FGLP represents the user location dataas relative points in an abstract 2D space, which enables learning acrossdifferent physical spaces. The model merges Bidirectional Long Short-TermMemory (BiLSTM) and Convolutional Neural Networks (CNN), where BiLSTM learnsthe speed and direction of the mobile users, and CNN learns information such asuser movement preferences. FGLP uses federated learning to protect user privacyand reduce bandwidth consumption. Our experimental results, using a datasetwith over 600,000 users, demonstrate that FGLP outperforms baseline models interms of prediction accuracy. We also demonstrate that FGLP works well inconjunction with transfer learning, which enables model reusability. Finally,benchmark results on several types of Android phones demonstrate FGLP'sfeasibility in real life.

FGLP: A Federated Fine-Grained Location Prediction System for Mobile Users