Traffic speed forecasting

The dataset is saved on Python's Numpy library format.The dataset is splitted in training and testing.X is the inputs and Y is the outputs.X is a feature-normalized 3D matrix (samples, time intervals, features).Y is a 2D matrix (samples, time intervals).<br>*X features are:speed_avg_1: Average speed on lane 1<br>speed_avg_2: Average speed on lane 2<br>speed_avg_3: Average speed on lane 3<br>speed_med_1: Median speed on lane 1<br>speed_med_2: Median speed on lane 2<br>speed_med_3: Median speed on lane 3<br>speed_min_1: Minimum speed on lane 1<br>speed_min_2: Minimum speed on lane 2<br>speed_min_3: Minimum speed on lane 3<br>speed_max_1: Maximum speed on lane 1<br>speed_max_2: Maximum speed on lane 2<br>speed_max_3: Maximum speed on lane 3<br>speed_std_1: Speed's standard deviation on lane 1<br>speed_std_2: Speed's standard deviation on lane 2<br>speed_std_3: Speed's standard deviation on lane 3<br>volume_1: Volume on lane 1<br>volume_2: Volume on lane 2<br>volume_3: Volume on lane 3<br>detected_1: (dummy) vehicle detected on lane 1<br>detected_2: (dummy) vehicle detected on lane 2<br>detected_3: (dummy) vehicle detected on lane 3<br>day_week_1: (dummy) day of the week = monday<br>day_week_2: (dummy) day of the week = tuesday<br>day_week_3: (dummy) day of the week = wednesday<br>day_week_4: (dummy) day of the week = thursday<br>day_week_5: (dummy) day of the week = friday<br>precipitation: rain intensity<br>*Y is the average speed of the time interval considering all lanes<br><i>*days</i> is a vector to indicate a day ID for each sample.<br>*<i>u</i> and <i>s</i> are the average and standard deviation used for normalization of X_train and X_test and calculated based on X_train<br>