Building A Tensorflow Lite Neural Network Vibration Classifier, With A Little Help From DSP

This presentation will walk through a Python Notebook that uses a combination of DSP and a Convolutional Neural Network (CNN) to classify multiple vibration modes of a rotating machine.
The key to developing an efficient vibration mode classifier is the use of DSP algorithms to optimize the task.
The DSP functions will pre-process the data to allow a simpler Neural Network to be used for the classification.
The CNN will use a Tensorflow model that is trained on the supplied data, it will then use the model to classify new data.
We will also include the code to generate and test both the Tensorflow and Tensorflow Lite models.
Once generated, we will test the Tensorflow Lite model to ensure it classifies the data as well as the floating point model.

Go to Session

Live Q&A - Building A Tensorflow Lite Neural Network Vibration Classifier, With A Little Help From DSP

Live Q&A with John Edwards for the talk titled Building A Tensorflow Lite Neural Network Vibration Classifier, With A Little Help From DSP

Go to Session

An Introduction To High Efficiency And Multi-rate Digital Filters

There are many ways to implement digital filters and many architectures that can be chosen to achieve the optimum performance, which is typically measured in terms of MIPS and memory. This presentation will describe several optimized filtering techniques and architectures and show how they are used.

Examples will include Comb, Polyphase, Cascaded Integrator Comb (CIC) and more.

Go to Session

Live Q&A with John Edwards - An Introduction To High Efficiency And Multi-rate Digital Filters

Live Q&A with John Edwards following his talk titled "An Introduction To High Efficiency And Multi-rate Digital Filters"

Go to Session

Frequency Domain Signal Processing (2020)

Frequency domain signal processing is not just about using the Fast Fourier Transform for calculating a power spectrum, it is also a very efficient method of processing signals compared to traditional time domain techniques. This presentation will describe several common frequency domain algorithms and show how they are used. Examples will include Frequency Domain Filtering, Time Delay Estimation and Interpolation; and more.

Go to Session

Live Q&A Discussion - Frequency Domain Signal Processing (2020)

This is a the live Q&A session for the talk given by John Edwards and titled 'Frequency Domain Signal Processing'

Go to Session