Audio Pre-processing and training with a CNN and a Linear classification

 


using the example instruction found on the https://towardsdatascience.com/audio-deep-learning-made-simple-sound-classification-step-by-step-cebc936bbe5 website.

 We will start with sound files, convert them into spectrograms, input them into a CNN plus Linear Classifier model, and produce predictions about the class to which the sound belongs.

Comments

Post a Comment

Popular posts from this blog

Drill visualization

Image
I manage to install the drill visualisation software and received a bit of training on how to navigate it. The ultimate objective of the drill visualisation is to use the prediction data from the flask API to visualise the drill up and down composition in replay mode. this is purely experimental and might not yield the expected result since we haven't used 3d data this far when building the model.
Read more

3D Geological Data Model, NON -Euclidean Data, Geological Deep Learning, and Graph Convolutional Networks

Image
After waiting some time, I received the 3D data for the panel that was mined on the days I selected to train the model against. I intend to train two models, one with geological 3d data and the other with drill bit data. The plan is that they will work together to achieve the desired outcome or to find an algorithm that will consider both data types and produce the binary classification with a distance in meters of how much to pick up the drill bit by. This will ultimately save time because you will not need to pull up the bit to the default 8 meters knowing the geology or lithology of the sea floor. Research into GCN (Graph Convolutional Networks ) I have also found this video that speaks about GCN. The content encourages using dynamic graph CNN for learning on point clouds, in our case the .xyz file. it also advised considering the points in a point cloud data as nodes in a directed graph. these models help learn from non- euclidean data like graphs and 3d objects using a different ...
Read more

Possible Output of the Machine Learning Model

Image
  Drillers mining parameter The ML model would focus on automating some if not most of the driller's functions performed to achieve timely drill bit composition.  Functions - the abovementioned function is the manual setting of the following mining parameter. Gravel -is the material extracted from the sea flow and pumped up onto the vessel for further processing. Mining airflow:  we need to take note that if the air pressure is too low, it will not be able to lift the gravel. Similarly, it's too high it will result in an overflow of gravel.  one needs to achieve a correct range else the incorrect values will cause blockages.      air pressure             The ideal air pressure should be within 7 to 10 bars, and it is mostly prepared at 8 bars.        airflow           The airflow ranges from 200 - 2600, but the prepared air flow is at 2200 (need to reconfirm these...
Read more