I have over 500 source files, each of which contains a multivariate time series sequence (same variables though). My objective is to develop a model that can find anomaly by checking the reconstruction error from LSTM (Long Short Term Memory model). Each file, has about 4000 - 5000 records of data. Since the no. of records in each file are not sufficient for LSTM to learn enough features, how do I combine different time series together and run LSTM ? Also, what would be other approaches in this case ?
Ina a case those LSTM files are text files, you are able to combine (merge) multiple text files into a single new file using the Windows command prompt only.
The simplest way to do this is to place all of the files that need to be merged into a single folder and then run the merging command from that folder:
copy *.lstm newfile.lstm
Anton Vrdoljak
As I mentioned in the question, these are not text files but time-series of multiple variables (all numeric in nature). By LSTM here, I meant Long Short Term Memory model (in deep learning context). Perhaps I should clarify this in the question.
I didn't understand well your question but , if you aim to develop equation use multi-objective optimization technique.
- Badges
- Science topic
- Similar topics
- Filing