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

Identifying systems with high-dimensional inputs and outputs, such as systemsmeasured by video streams, is a challenging problem with numerous applicationsin robotics, autonomous vehicles and medical imaging. In this paper, we proposea novel non-linear state-space identification method starting fromhigh-dimensional input and output data. Multiple computational and conceptualadvances are combined to handle the high-dimensional nature of the data. Anencoder function, represented by a neural network, is introduced to learn areconstructability map to estimate the model states from past inputs andoutputs. This encoder function is jointly learned with the dynamics.Furthermore, multiple computational improvements, such as an improvedreformulation of multiple shooting and batch optimization, are proposed to keepthe computational time under control when dealing with high-dimensional andlarge datasets. We apply the proposed method to a video stream of a simulatedenvironment of a controllable ball in a unit box. The study shows lowsimulation error with excellent long term prediction capability of the modelobtained using the proposed method.

Non-linear State-space Model Identification from Video Data using Deep Encoders