0
$\begingroup$

I have text data representing sensor outputs.

Dataset:

1458996986002;    11.43,-15.86,11.20,508.26;        -1.59,-0.22,6.17,40.68;        126.0,-150.9,-105.0,49671.81;        Walk
1459002923002;    16.69,-12.68,13.96,634.65;        -2.55,2.13,4.87,34.87;         126.0,-150.9,-105.0,49671.81;        Walk


timestamp;    acc_x,acc_y,acc_z;    gyro_x,gyro_y,gyro_z;    magn_x,magn_y,magn_z;    ActivityName

My Goal: I would like to extract features from the text lines before feeding it into a Recurrent Neural Network (GRU/LSTM). So, my goal is automatic feature extraction. Those extracted features (encoder network) will be used before the neural network for an activity recognition task (classification).

My Question: Which Autoencoder (denoising, variational, sparse) is suitable for such dataset? Or should I use RBM instead? After choosing a feature extraction method, how do I compare the output with input, since the input is not 0s and 1s?

What I have read: I read that RBM is generative model, which, even if you give some similar input, it can generate similar correct output. And training autoencoder is said(1) to be easier(2) than RBM. On the other hand, variational autoencoder can do something similar (generative). First question would be is having generative ability has any advantage for above problem, because at the end of pretraining i would just use encoder part and throw decoder layers? If no, denoising autoencoder seems right approach I'm my opinion.

Last thing: I know to force network to learn important features from data (instead of memorizing), you can choose following methods: 1) use sandwich like layers, 2) add noise to input 3) regularize autoencoder=make only some nodes active at the same time

$\endgroup$
  • $\begingroup$ Also i will be providing about 100 readings at once (based on window size like 2seconds) to autoencoder $\endgroup$ – Jemshit Iskenderov Mar 21 '18 at 6:42
0
$\begingroup$

Because you want to do activity recognition based on time windows using deep learning models with autoencoders I would strongly suggest to have a look at the following articles:

https://www.researchgate.net/publication/323019783_An_Effective_Deep_Autoencoder_Approach_for_Online_Smartphone-Based_Human_Activity_Recognition It gives an overview of a custom CNN/RNN model which might give an initial idea of how to proceed for the specific task of AR.

and

https://ieeexplore.ieee.org/document/8422895 It gives a general idea of how to reconstruct sensor data with semantic meanings before feeding the constructed data features to another model.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.