Table 2 Hyperparameter settings for random forest model in fall risk classification.

From: Interpretable and lightweight fall detection in a heritage gallery using YOLOv11-SEFA for edge deployment

Hyperparameter

Description

Value range

Number of Trees (numTrees)

Number of decision trees in the random forest

{10, 50, 100, 150}

Maximum Depth (maxDepth)

Controls the complexity of individual decision trees

{2, 5, 10, 20}

Maximum Features (maxFeatures)

Number of features considered at each split

\(\:\left(\sqrt{d},\frac{d}{3}\right)\) (where \(\:d\) is the total number of features)

Minimum Samples per Leaf (minSamplesLeaf)

Minimum number of samples required to be at a leaf node

{1, 5, 10, 20, 50, 100}

  1. The above parameter adjustment strategy aims to achieve a balance between capturing fine-grained data regularities and preventing overfitting, thereby improving the robustness and generalization ability of the model.
Back to article page