I need to create a simple Recurrent Neural Network RNN or Long short-term memory (LSTM), which is specific type of RNN. After searching through examples and forums I haven't come across many applications that are similar enough to my project. I tried to implement a simple RNN to classify the ECG signals into two classes, but no luck so far. I'm confused about What is the correct input shape for the model?.
Let say I have 20 ECG record. My input data is such that I have m=20 signals each with n=7000 data points, and L=2 output labels that I am trying to learn. How I should structuring my input data. Is it true to make the input as (m,n,1) and output targets as (m,L)!.
I attempt to use the following Matlab toolboxes for building the RNN:
https://github.com/yechengxi/LightNet.
Please help!
From the data and the task you describe, with a very small set of very high-dimensional independent data samples, it seems to me a RNN or LSTM is a poor choice (which probably explains the rarity of similar examples). In any case, should you want to use an RNN/LSTM anyway, the input and output dimensions depend on how you set up the model, and with which toolbox. One way is for the input to be of dimension (20, 7000), and the output to be (20,2). Note that you can have the network just produce the probability for a data sample to be in e.g. class 1, in which case (20,1) would work just as well. Again, it's up to you, and how you set up the model.
Note also that given the number of parameters in your network, and the size of your training set, your RNN will probably severely overtrain, unless you take a host of measures to prevent it (dropout, regularization, leave-one-out cross-validation, etc...). Even so, I am skeptical about making this work. If I had to solve this problem, I would probably look towards something like support vector machines.
Hope that helps. Good luck!
I recommend to use SVM instead of neural networks, because most researchers proved that SVM is more powerful than neural networks in classification tasks. From my experience, SVM will be simpler to implement and test on your data and more understood.
Hey there, you can start with a simple sliding window approach. First prepare your sliding window, set how much is the length of your window and slide that sliding window one step at a time. These sliding window of your data would be the feature for your study. Now for each sliding window, place a desired class. This will be the labels.
You can then build your LSTM classifier using the sliding windows as input.
If you want an example you can check out this Jupyter notebook. The notebook contains a section on how to generate the sliding window from the data. You can either get that code and convert to Matlab or create a python script out of the snippet.
https://github.com/cadrev/lstm-flood-prediction/blob/master/lstm_flood.ipynb
What is the point of using a recurrent neural network for classifying ECG heartbeats ? Recurrent neural networks are useful for modeling dynamic processes, which, in your case, would just be a time series, without exogenous inputs (contrary to flood prediction mentioned above). The reason why you did not find any similar example in the literature is probably that it is a bad idea, in addition to the very sensible arguments provided by the first answer above.
There is a huge literature on hearbeat classification, using loads of different classifiers (including neural networks and SVMs); all state-of-the art classifiers provide basically the same results, which are very good because hearbeat classification is a simple problem if it is addressed correctly.
In my view, the key issue in heartbeat classification (as in most classification problems) is to use a maximum amount of expert knowledge in order to find an appropriate representation of the data. If you find an original data representation, more efficient than usual ones, you will make a nice scientific contribution; but I am afraid that trying to perform heartbeat classification with recurrent neural networks won't lead you anywhere. Sorry for being negative!
- Badges
- Science topic