Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Literature review.

More »

Table 1 Expand

Fig 1.

Flow chart of proposed system.

More »

Fig 1 Expand

Fig 2.

Punch types and its kinematics: (a) No punch (b) Long-range rear jab to head (c) Mid-range rear hook to head (d) Mid-range rear uppercut to head.

More »

Fig 2 Expand

Fig 3.

IMU raw data: (a) 3-DoF accelerometer data (b) 3-DoF gyroscope data.

More »

Fig 3 Expand

Fig 4.

IMU data and video synchronization.

More »

Fig 4 Expand

Fig 5.

Expert annotation of uncertain instances to refine model training.

More »

Fig 5 Expand

Table 2.

Accuracy metrics with different percentage of the training dataset.

More »

Table 2 Expand

Fig 6.

Combined Confusion matrix: (a) Rear hand punch recognition (b) Lead hand punch recognition.

More »

Fig 6 Expand

Table 3.

Model testing results across different boxers with 15% of training dataset.

More »

Table 3 Expand

Fig 7.

Combined Confusion matrix: (a) Rear hand punch classification (b) Lead hand punch classification.

More »

Fig 7 Expand

Fig 8.

Confusion matrix-punch classification.

More »

Fig 8 Expand

Fig 9.

Validation of punch with timestamp: (a) Jab (b) Hook (c) Uppercut.

More »

Fig 9 Expand

Table 4.

Literature comparison.

More »

Table 4 Expand