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

Intelligent vehicle anticipation of the movement intentions of other driverscan reduce collisions. Typically, when a human driver of another vehicle(referred to as the target vehicle) engages in specific behaviors such aschecking the rearview mirror prior to lane change, a valuable clue is thereinprovided on the intentions of the target vehicle's driver. Furthermore, thetarget driver's intentions can be influenced and shaped by their drivingenvironment. For example, if the target vehicle is too close to a leadingvehicle, it may renege the lane change decision. On the other hand, a followingvehicle in the target lane is too close to the target vehicle could lead to itsreversal of the decision to change lanes. Knowledge of such intentions of allvehicles in a traffic stream can help enhance traffic safety. Unfortunately,such information is often captured in the form of images/videos. Utilization ofpersonally identifiable data to train a general model could violate userprivacy. Federated Learning (FL) is a promising tool to resolve this conundrum.FL efficiently trains models without exposing the underlying data. This paperintroduces a Personalized Federated Learning (PFL) model embedded a longshort-term transformer (LSTR) framework. The framework predicts drivers'intentions by leveraging in-vehicle videos (of driver movement, gestures, andexpressions) and out-of-vehicle videos (of the vehicle's surroundings -frontal/rear areas). The proposed PFL-LSTR framework is trained and testedthrough real-world driving data collected from human drivers at Interstate 65in Indiana. The results suggest that the PFL-LSTR exhibits high adaptabilityand high precision, and that out-of-vehicle information (particularly, thedriver's rear-mirror viewing actions) is important because it helps reducefalse positives and thereby enhances the precision of driver intentioninference.

PFL-LSTR: A privacy-preserving framework for driver intention inference based on in-vehicle and out-vehicle information