Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
en.osm.town is one of the many independent Mastodon servers you can use to participate in the fediverse.
An independent, community of OpenStreetMap people on the Fediverse/Mastodon. Funding graciously provided by the OpenStreetMap Foundation.

Administered by:

Server stats:

251
active users

en.osm.town: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#signalprocessing

0 posts0 participants0 posts today
Public
Neural

I’m giving a ‘special talk’ on April 12 (tomorrow) at 14:00 at @clab.tw 科技媒體實驗平台 in Taipei (Taiwan), about “Temporary and Distributed Libraries, active and independent librarianship”, as part of the great Radiotopia event co-organised by the Toolkit of Care project and C-LAB, with artists and activists using radio as a medium and a concept, curated by @shulea2, and coordinated by @stwst_linz (Linz, Austria) and @agenceapo33 (Nantes, France).
radiotopia.clab.org.tw/

#antenna #signalprocessing #audioart #binaural #electromagnetic #interference #microphones #audiorecording #radio #radioart #radiowaves #transmissionart #soundfrequency #sound #soundart #soundartist #klangkunst #soundinstallation #soundartinstallation #soundsculpture
#soundscapes #acousticspace #sonicworld #vibration #soundarchive #audiology #soundscience #soundstudies

Radiotopia manifesto
Radiotopia participants
Public
amen zwa, esq.

Speaking as an #EE, I'm vexed that #complex-valued #NeuralNetwork #CVNN didn't take hold outside the #SignalProcessing community. Sure, there's Liouville's Theorem and other hurdles, but CVNNs are great for all things #wave-like—as in real-life #signals.

link.springer.com/article/10.1

SpringerLinkNature of complex number and complex-valued neural networks - Frontiers of Electrical and Electronic EngineeringWe discuss the nature of complex number and its effect on complex-valued neural networks (CVNNs). After we review some examples of CVNN applications, we look back at the mathematical history to elucidate the features of complex number, in particular to confirm the importance of the phase-and-amplitude viewpoint for designing and constructing CVNNs to enhance the features. This viewpoint is essential in general to deal with waves such as electromagnetic wave and lightwave. Then, we point out that, although we represent a complex number as an ordered pair of real numbers for example, we can reduce ineffective degree of freedom in learning or self-organization in CVNNs to achieve better generalization characteristics. This merit is significantly useful not only for waverelated signal processing but also for general processing with frequency-domain treatment through Fourier transform.
Public *
Albert Cardona

"Binlets: Data fusion-aware denoising enables accurate and unbiased quantification of multichannel signals", Silberberg & Grecco, 2023 sciencedirect.com/science/arti

Old school signal processing, not based on machine learning but instead on a translation-invariant Haar wavelet decomposition, profitably exploiting correlations across channels. The manuscript includes an accessible and brief "Theory" section and a longer appendix. All it needs to run is a test function between two data points.

In their benchmarks and use cases, the new method outperforms existing denoising methods. In both time series and on fluorescent microscopy images.

There's a repository available github.com/maurosilber/binlets and can be installed with `pip install binlets`.

Fig. 6. Denoising applied to fluorescence microscopy images of cells. (left) Intensity images for the ground truth, raw, and raw denoised with binlets and two deep learning methods (N2N and DnCNN). The color scale changes slope at 9 to highlight differences in three areas: nucleus, the rest of the cell, and background. Residuals were calculated against the ground truth, which is the average of 50 raw images, and normalized with their standard deviation. (top-right) Mean and standard deviation for the metrics applied to the whole dataset: root mean squared error improvement (RMSE improv., normalized to raw) and mean bias. They were calculated in three regions: the whole image (all), background and cell areas. (bottom right) Residual mean intensity for each nucleus between the denoised and ground truth images as a function of the ground truth mean intensity. The error bars correspond to the standard deviation of the 50 samples.
#denoising#SignalProcessing#wavelets
ExploreLive feeds
About