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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Recent advances in deep learning motivate the use of deep neural networks inInternet-of-Things (IoT) applications. These networks are modelled after signalprocessing in the human brain, thereby leading to significant advantages atperceptual tasks such as vision and speech recognition. IoT applications,however, often measure physical phenomena, where the underlying physics (suchas inertia, wireless signal propagation, or the natural frequency ofoscillation) are fundamentally a function of signal frequencies, offeringbetter features in the frequency domain. This observation leads to afundamental question: For IoT applications, can one develop a new brand ofneural network structures that synthesize features inspired not only by thebiology of human perception but also by the fundamental nature of physics?Hence, in this paper, instead of using conventional building blocks (e.g.,convolutional and recurrent layers), we propose a new foundational neuralnetwork building block, the Short-Time Fourier Neural Network (STFNet). Itintegrates a widely-used time-frequency analysis method, the Short-Time FourierTransform, into data processing to learn features directly in the frequencydomain, where the physics of underlying phenomena leave better foot-prints.STFNets bring additional flexibility to time-frequency analysis by offeringnovel nonlinear learnable operations that are spectral-compatible. Moreover,STFNets show that transforming signals to a domain that is more connected tothe underlying physics greatly simplifies the learning process. We demonstratethe effectiveness of STFNets with extensive experiments. STFNets significantlyoutperform the state-of-the-art deep learning models in all experiments. ASTFNet, therefore, demonstrates superior capability as the fundamental buildingblock of deep neural networks for IoT applications for various sensor inputs.

STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks