GRU. (a) and (b) present boxplots displaying the FAR and F1 score across various features, i.e., Force, Displacement, and F&D, utilizing a constant number of hidden layers (100), learning rate (0.0006), and minibatch size (128). (c) and (d) showcase boxplots representing FAR and F1 score variations, depicting changes in the number of hidden layers while maintaining F&D as the feature set, along with a fixed learning rate of 0.0006 and minibatch size of 128. Finally, (e) and (f) exhibit boxplots illustrating differences in FAR and F1 score based on different learning rates, while keeping the number of hidden layers constant at 80, utilizing F&D as the feature set, and minibatch size of 128. The boxplots are represented with a box having a horizontal line in the center, with horizontal lines extending from each side (referred to as "whiskers"). The box represents the interquartile range (IQR), encapsulating 50% of data points falling between the first quartile and the third quartile in the dataset. The outcomes corresponding to training and validation are distinguished by black and red colors, respectively.