Machine Intelligence at the Crease: A Quintuple-Class CNN-LSTM Model for Umpire Gesture Recognition

The model is advanced and state-of-the-art. How successful can a methodology be assessed in identifying essential performance practicalities and applying them to all five umpire actions accomplished? The precisions, recall, and F1 scores have been measured correctly; this allows us to quantify the model’s prediction accuracy. For Class 1, which is facile to detect, the precision record was higher than 87.3%, with a recall of $\mathbf{9 7. 3 \%}$ and an F 1 score of 92.1%. A fantastic level of accuracy characterizes class 2, as it reported a high precision of above 87% and a recall of above 94%, with F1-score precision above $\mathbf{9 0 \%}$. The Grade 3 model displays an accuracy of 86.94%, a recall of 84.12%, and an F1-score of 85.50. The precision for Class 4 is 89%, with a sensitivity of 81% and an $F 1$ score of 85%. Its accuracy is 90.43%, and its recall is 87.93%, so the F1 score is also 89.16%. Among the averaging techniques, macro, micro, and weighted averages incorporate class-wise errors and summarise the entire model performance. The macro average indicates that the accuracy, number of articles returned, and F1 score are 88.27 %, 89.02 %, and 88.51%, respectively. The weighted average is concerned with the weighted class distribution, which provides accuracy, recall, and F1 of 88.38%, 88.32%, and 88.23%, respectively. The micro average results from all courses’ total contributions show a global performance of 88.32% in accuracy, recall, and F1 score. Moreover, the accuracy rate of the proposed model will astonish anyone at 88.3%. When we add it up, it is evident that the CNN-LSTM model, which we use to recognize umpire actions automatically, is an accurate statement. This model displays the possibility of a dramatic increase in the accuracy and dependability of the cricket referee.