import numpy as np

def boundary_fitness(yanlinks):
    unique_values, unique_indices = np.unique(yanlinks[:, 11], return_index=True)
    Tvb = 0
    for i in unique_values:
        selected_values = yanlinks[yanlinks[:, 11] == i][:, 5]
        variance = np.var(selected_values)
        Tvb += variance
    return Tvb