Understanding Time Series Data for Classification

I have collected data from numerous volunteers driving a simulator in 8 different scenarios (classes). A volunteer drives in a map for 4 minutes in one scenario (one experiment), then he drives in the same map for 4 minutes in a different scenario(second experiment).

Our current dataset has around 0.4 million rows of driving data.

Let us consider volunteer 1 (henceforth V1), He drives in Day Non-distracted (DN) scenario producing N rows (say 1000). He drives in Day Distracted (DD) scenario producing N rows ( say 1000). . . . For eight scenarios, thus producing around 8000 rows of driving data.

Volunteer 2 ( V2) produces 8000 rows of driving data. And we have collected data from around 52 volunteers. So we have 52 * 8000 rows of data rows in total. The data looks like this.

In our current approach, we are saving the mode corresponding to each data points in the one hot format and we expect the deep neural network to crunch the numbers one data row at a time and form a relation between these 9 features and the 8 classes.

I would like to build a neural network model which will help me classify the data into 8 classes.

How do I proceed from here? Is this data a time series data? Does looking at each row of driving data make any sense? or should I be looking at the entire data rows of V1 in DN scenario as one input ?

Right now I am just doing a multi layer perceptron model, expecting the system to crunch the 9 features and find a relation to the mode. But somehow I feel that’s not the way to look at this data.

I am very new to machine learning. Any help would be great. Thanks in advance.