I am currently working on creating a time series dataset for a machine learning/deep learning project, focusing on medical inspection values. The dataset is structured such that each row has a different inspection time, with values recorded at 6-hour intervals within a 96-hour window, resulting in 16 data points per cell. Here is an example of how the data is formatted:
Given this structure, I have a couple of questions:
Is this a suitable way to represent time series data for machine learning/deep learning purposes? Are there any potential issues or improvements that could be made to better capture the temporal dynamics of the data?
Given the nature of the data and the task at hand (classifying 'class'), what machine learning or deep learning models would be most appropriate? I am particularly interested in models that are well-suited for time series data and can effectively handle the sequential nature of the information.
Any insights, recommendations, or resources you could provide would be greatly appreciated. Thank you in advance for your time and assistance!
I will do data imputation and before that I want to know if time series data can be like this.