The dataset includes the raw data used for training and testing with data aggregation levels of 30 minutes and 60 minutes.

The data collection period is from April 13, 2014 to May 9, 2014. Data from April 13 to May 4 are utilized for training models, and the remaining data are utilized for testing and prediction. For each CSV (Comma-Separated Values) file, the first row indicates the road link IDs in the entire network, and the other rows indicates the traffic conditions for each time interval, where 0 represents uncongested and 1 represents congested. The congestion threshold is set as 20 kilometers per hour. The algorithm execution results are saved in two CSV files. The file named as “result.csv” records both accuracy and cross-entropy value for each iteration, and the other file named as “sequence.csv” records the predicted traffic congestion patterns using the RBM-RNN model. (ZIP)